Search Results for author:
Found 225 papers, 82 papers with code
Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment.
Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning
We further propose a novel online learning algorithm that achieves such improved regret without knowing this parameter in advance, i. e., automatically adapting to task similarity.
Model-based Causal Bayesian Optimization
We formalize this generalization of CBO as Adversarial Causal Bayesian Optimization (ACBO) and introduce the first algorithm for ACBO with bounded regret: Causal Bayesian Optimization with Multiplicative Weights (CBO-MW).
Submodular Reinforcement Learning
In many important applications, such as coverage control, experiment design and informative path planning, rewards naturally have diminishing returns, i. e., their value decreases in light of similar states visited previously.
Anytime Model Selection in Linear Bandits
This allows us to develop ALEXP, which has an exponentially improved ($\log M$) dependence on $M$ for its regret.
Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning
Many applications, e. g., in shared mobility, require coordinating a large number of agents.
Safe Risk-averse Bayesian Optimization for Controller Tuning
Controller tuning and parameter optimization are crucial in system design to improve both the controller and underlying system performance.
Optimistic Active Exploration of Dynamical Systems
In our experiments, we compare OPAX with other heuristic active exploration approaches on several environments.
Unbalanced Diffusion Schrödinger Bridge
Schr\"odinger bridges (SBs) provide an elegant framework for modeling the temporal evolution of populations in physical, chemical, or biological systems.
Provably Learning Nash Policies in Constrained Markov Potential Games
Multi-agent reinforcement learning (MARL) addresses sequential decision-making problems with multiple agents, where each agent optimizes its own objective.
Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
In this paper, we present a data-driven strategy to simplify the deployment of model-based controllers in legged robotic hardware platforms.
Learning Safety Constraints from Demonstrations with Unknown Rewards
We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a set of safe demonstrations with possibly different reward functions.
A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks
We show how this spectral bias towards low-degree frequencies can in fact hurt the neural network's generalization on real-world datasets.
Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement
Spinal fusion surgery requires highly accurate implantation of pedicle screw implants, which must be conducted in critical proximity to vital structures with a limited view of anatomy.
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance.
Aligned Diffusion Schrödinger Bridges
Diffusion Schr\"odinger bridges (DSB) have recently emerged as a powerful framework for recovering stochastic dynamics via their marginal observations at different time points.
Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications
Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models.
Learning To Dive In Branch And Bound
Primal heuristics are important for solving mixed integer linear programs, because they find feasible solutions that facilitate branch and bound search.
Near-optimal Policy Identification in Active Reinforcement Learning
Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces.
Model-based Causal Bayesian Optimization
How should we intervene on an unknown structural equation model to maximize a downstream variable of interest?
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice
Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks.
Isotropic Gaussian Processes on Finite Spaces of Graphs
We propose a principled way to define Gaussian process priors on various sets of unweighted graphs: directed or undirected, with or without loops.
Instance-Dependent Generalization Bounds via Optimal Transport
Existing generalization bounds fail to explain crucial factors that drive generalization of modern neural networks.
Lifelong Bandit Optimization: No Prior and No Regret
Our algorithm can be paired with any kernelized or linear bandit algorithm and guarantees oracle optimal performance, meaning that as more tasks are solved, the regret of LIBO on each task converges to the regret of the bandit algorithm with oracle knowledge of the true kernel.
Leveraging Demonstrations with Latent Space Priors
Starting with a learned joint latent space, we separately train a generative model of demonstration sequences and an accompanying low-level policy.
A Dynamical System View of Langevin-Based Non-Convex Sampling
Non-convex sampling is a key challenge in machine learning, central to non-convex optimization in deep learning as well as to approximate probabilistic inference.
MARS: Meta-Learning as Score Matching in the Function Space
To circumvent these issues, we approach meta-learning through the lens of functional Bayesian neural network inference, which views the prior as a stochastic process and performs inference in the function space.
Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
Contextual Bayesian optimization (CBO) is a powerful framework for sequential decision-making given side information, with important applications, e. g., in wind energy systems.
Near-Optimal Multi-Agent Learning for Safe Coverage Control
In this paper, we aim to efficiently learn the density to approximately solve the coverage problem while preserving the agents' safety.
Replicable Bandits
Similarly, for stochastic linear bandits (with finitely and infinitely many arms) we develop replicable policies that achieve the best-known problem-independent regret bounds with an optimal dependency on the replicability parameter.
Meta-Learning Priors for Safe Bayesian Optimization
In the presence of unknown safety constraints, it is crucial to choose reliable model hyper-parameters to avoid safety violations.
Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning
We introduce a general approach for seeking a stationary point in high dimensional non-linear stochastic optimization problems in which maintaining safety during learning is crucial.
Active Exploration for Inverse Reinforcement Learning
We propose a novel IRL algorithm: Active exploration for Inverse Reinforcement Learning (AceIRL), which actively explores an unknown environment and expert policy to quickly learn the expert's reward function and identify a good policy.
Graph Neural Network Bandits
By establishing a novel connection between such kernels and the graph neural tangent kernel (GNTK), we introduce the first GNN confidence bound and use it to design a phased-elimination algorithm with sublinear regret.
Safe Reinforcement Learning via Confidence-Based Filters
Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems.
Active Exploration via Experiment Design in Markov Chains
A key challenge in science and engineering is to design experiments to learn about some unknown quantity of interest.
Supervised Training of Conditional Monge Maps
To account for that context in OT estimation, we introduce CondOT, a multi-task approach to estimate a family of OT maps conditioned on a context variable, using several pairs of measures $\left(\mu_i, \nu_i\right)$ tagged with a context label $c_i$.
Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning
Cutting planes are essential for solving mixed-integer linear problems (MILPs), because they facilitate bound improvements on the optimal solution value.
Invariant Causal Mechanisms through Distribution Matching
Learning representations that capture the underlying data generating process is a key problem for data efficient and robust use of neural networks.
Riemannian stochastic approximation algorithms
We examine a wide class of stochastic approximation algorithms for solving (stochastic) nonlinear problems on Riemannian manifolds.
Interactively Learning Preference Constraints in Linear Bandits
We provide an instance-dependent lower bound for constrained linear best-arm identification and show that ACOL's sample complexity matches the lower bound in the worst-case.
Active Bayesian Causal Inference
In this work, we propose Active Bayesian Causal Inference (ABCI), a fully-Bayesian active learning framework for integrated causal discovery and reasoning, which jointly infers a posterior over causal models and queries of interest.
BaCaDI: Bayesian Causal Discovery with Unknown Interventions
Inferring causal structures from experimentation is a central task in many domains.
Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces
In this work, we investigate the optimal design of experiments for {\em estimation of linear functionals in reproducing kernel Hilbert spaces (RKHSs)}.
Amortized Inference for Causal Structure Learning
Rather than searching over structures, we train a variational inference model to directly predict the causal structure from observational or interventional data.
Gradient-Based Trajectory Optimization With Learned Dynamics
In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car, and gives good performance in combination with trajectory optimization methods.
Multi-Scale Representation Learning on Proteins
This paper introduces a multi-scale graph construction of a protein -- HoloProt -- connecting surface to structure and sequence.
Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization
Tuning machine parameters of particle accelerators is a repetitive and time-consuming task that is challenging to automate.
Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environment.
The Schrödinger Bridge between Gaussian Measures has a Closed Form
The static optimal transport $(\mathrm{OT})$ problem between Gaussians seeks to recover an optimal map, or more generally a coupling, to morph a Gaussian into another.
A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
We consider the sequential optimization of an unknown, continuous, and expensive to evaluate reward function, from noisy and adversarially corrupted observed rewards.
Meta-Learning Hypothesis Spaces for Sequential Decision-making
We demonstrate our approach on the kernelized bandit problem (a. k. a.~Bayesian optimization), where we establish regret bounds competitive with those given the true kernel.
Constrained Policy Optimization via Bayesian World Models
Improving sample-efficiency and safety are crucial challenges when deploying reinforcement learning in high-stakes real world applications.
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
Protein complex formation is a central problem in biology, being involved in most of the cell's processes, and essential for applications, e. g. drug design or protein engineering.
Misspecified Gaussian Process Bandit Optimization
Instead, we introduce a \emph{misspecified} kernelized bandit setting where the unknown function can be $\epsilon$--uniformly approximated by a function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS).
Risk-averse Heteroscedastic Bayesian Optimization
We generalize BO to trade mean and input-dependent variance of the objective, both of which we assume to be unknown a priori.
Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems
To this end, neural ODEs regularized with neural Lyapunov functions are a promising approach when states are fully observed.
Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes
In Bayesian Optimization (BO) we study black-box function optimization with noisy point evaluations and Bayesian priors.
Sensing Cox Processes via Posterior Sampling and Positive Bases
We study adaptive sensing of Cox point processes, a widely used model from spatial statistics.
Hierarchical Skills for Efficient Exploration
We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner.
Data Summarization via Bilevel Optimization
We show the effectiveness of our framework for a wide range of models in various settings, including training non-convex models online and batch active learning.
Contextual Games: Multi-Agent Learning with Side Information
We formulate the novel class of contextual games, a type of repeated games driven by contextual information at each round.
Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning
Learning in multi-agent systems is highly challenging due to several factors including the non-stationarity introduced by agents' interactions and the combinatorial nature of their state and action spaces.
Neural Contextual Bandits without Regret
Contextual bandits are a rich model for sequential decision making given side information, with important applications, e. g., in recommender systems.
Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models
Differential equations in general and neural ODEs in particular are an essential technique in continuous-time system identification.
PopSkipJump: Decision-Based Attack for Probabilistic Classifiers
Most current classifiers are vulnerable to adversarial examples, small input perturbations that change the classification output.
Proximal Optimal Transport Modeling of Population Dynamics
We propose to model these trajectories as collective realizations of a causal Jordan-Kinderlehrer-Otto (JKO) flow of measures: The JKO scheme posits that the new configuration taken by a population at time $t+1$ is one that trades off an improvement, in the sense that it decreases an energy, while remaining close (in Wasserstein distance) to the previous configuration observed at $t$.
Robust Generalization despite Distribution Shift via Minimum Discriminating Information
Training models that perform well under distribution shifts is a central challenge in machine learning.
Meta-Learning Reliable Priors in the Function Space
When data are scarce meta-learning can improve a learner's accuracy by harnessing previous experience from related learning tasks.
Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning
By running fixed point iteration for multiple steps, we achieve a trajectory of the valuations, among which we define the valuation with the best conceivable decoupling error as the Variational Index.
Learning Graph Models for Template-Free Retrosynthesis
Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule.
Ranked #5 on
Single-step retrosynthesis
on USPTO-50k
Addressing the Long-term Impact of ML Decisions via Policy Regret
To capture the long-term effects of ML-based allocation decisions, we study a setting in which the reward from each arm evolves every time the decision-maker pulls that arm.
Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
We propose an end-to-end trainable framework that processes large-scale visual data tensors by looking at a fraction of their entries only.
Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning
Causal structure learning is a key problem in many domains.
Bias-Robust Bayesian Optimization via Dueling Bandits
We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder.
DiBS: Differentiable Bayesian Structure Learning
In this work, we propose a general, fully differentiable framework for Bayesian structure learning (DiBS) that operates in the continuous space of a latent probabilistic graph representation.
A note on the CAPM with endogenously consistent market returns
I demonstrate that with the market return determined by the equilibrium returns of the CAPM, expected returns of an asset are affected by the risks of all assets jointly.
Regret Bounds for Gaussian-Process Optimization in Large Domains
These regret bounds illuminate the relationship between the number of evaluations, the domain size (i. e. cardinality of finite domains / Lipschitz constant of the covariance function in continuous domains), and the optimality of the retrieved function value.
Automatic Termination for Hyperparameter Optimization
Across an extensive range of real-world HPO problems and baselines, we show that our termination criterion achieves a better trade-off between the test performance and optimization time.
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
In real-world tasks, reinforcement learning (RL) agents frequently encounter situations that are not present during training time.
Model-based Reinforcement Learning
reinforcement-learning
+1
Information Directed Reward Learning for Reinforcement Learning
For many reinforcement learning (RL) applications, specifying a reward is difficult.
Risk-Averse Offline Reinforcement Learning
We demonstrate empirically that in the presence of natural distribution-shifts, O-RAAC learns policies with good average performance.
Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback
Combinatorial bandits with semi-bandit feedback generalize multi-armed bandits, where the agent chooses sets of arms and observes a noisy reward for each arm contained in the chosen set.
Safe and Efficient Model-free Adaptive Control via Bayesian Optimization
Thus, our approach builds on GoOSE, an algorithm for safe and sample-efficient Bayesian optimization.
Meta-Learning Bayesian Neural Network Priors Based on PAC-Bayesian Theory
Bayesian deep learning is a promising approach towards improved uncertainty quantification and sample efficiency.
Logistic Q-Learning
We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs.
Semi-supervised Batch Active Learning via Bilevel Optimization
Active learning is an effective technique for reducing the labeling cost by improving data efficiency.
Online Active Model Selection for Pre-trained Classifiers
Given $k$ pre-trained classifiers and a stream of unlabeled data examples, how can we actively decide when to query a label so that we can distinguish the best model from the rest while making a small number of queries?
Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator
Gradient estimation in models with discrete latent variables is a challenging problem, because the simplest unbiased estimators tend to have high variance.
Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases
Many applications of machine learning on discrete domains, such as learning preference functions in recommender systems or auctions, can be reduced to estimating a set function that is sparse in the Fourier domain.
Learning to Play Sequential Games versus Unknown Opponents
We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action.
Stochastic Linear Bandits Robust to Adversarial Attacks
We consider a stochastic linear bandit problem in which the rewards are not only subject to random noise, but also adversarial attacks subject to a suitable budget $C$ (i. e., an upper bound on the sum of corruption magnitudes across the time horizon).
Continuous Submodular Function Maximization
We start by a thorough characterization of the class of continuous submodular functions, and show that continuous submodularity is equivalent to a weak version of the diminishing returns (DR) property.
Safe Reinforcement Learning via Curriculum Induction
In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly.
Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory
The principal task to control dynamical systems is to ensure their stability.
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
Based on this theoretical foundation, we show how optimistic exploration can be easily combined with state-of-the-art reinforcement learning algorithms and different probabilistic models.
Model-based Reinforcement Learning
reinforcement-learning
+1
Gradient Estimation with Stochastic Softmax Tricks
The Gumbel-Max trick is the basis of many relaxed gradient estimators.
Learning Graph Models for Retrosynthesis Prediction
Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule.
Structured Variational Inference in Partially Observable Unstable Gaussian Process State Space Models
Finally, we show experimentally that our learning algorithm performs well in stable and unstable real systems with hidden states.
Safe non-smooth black-box optimization with application to policy search
For safety-critical black-box optimization tasks, observations of the constraints and the objective are often noisy and available only for the feasible points.
Coresets via Bilevel Optimization for Continual Learning and Streaming
Coresets are small data summaries that are sufficient for model training.
From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models
Submodular functions have been studied extensively in machine learning and data mining.
Hierarchical Image Classification using Entailment Cone Embeddings
Image classification has been studied extensively, but there has been limited work in using unconventional, external guidance other than traditional image-label pairs for training.
SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives
Gaussian processes are an important regression tool with excellent analytic properties which allow for direct integration of derivative observations.
Corruption-Tolerant Gaussian Process Bandit Optimization
We consider the problem of optimizing an unknown (typically non-convex) function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit feedback.
Mixed Strategies for Robust Optimization of Unknown Objectives
We consider robust optimization problems, where the goal is to optimize an unknown objective function against the worst-case realization of an uncertain parameter.
Information Directed Sampling for Linear Partial Monitoring
Partial monitoring is a rich framework for sequential decision making under uncertainty that generalizes many well known bandit models, including linear, combinatorial and dueling bandits.
Distributionally Robust Bayesian Optimization
Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is worst-case robust under a specified distributional shift of an uncontrolled covariate.
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
Meta-learning can successfully acquire useful inductive biases from data.
Efficiently Learning Fourier Sparse Set Functions
In this paper we consider the problem of efficiently learning set functions that are defined over a ground set of size $n$ and that are sparse (say $k$-sparse) in the Fourier domain.
A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness
Our family of fairness notions corresponds to a new interpretation of economic models of Equality of Opportunity (EOP), and it includes most existing notions of fairness as special cases.
Safe Exploration for Interactive Machine Learning
Existing algorithms for this problem learn about the safety of all decisions to ensure convergence.
Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by maximizing an exogenous reward signal while interacting with its environment.
Adaptive Sampling for Stochastic Risk-Averse Learning
In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples.
Convergence Analysis of Block Coordinate Algorithms with Determinantal Sampling
We analyze the convergence rate of the randomized Newton-like method introduced by Qu et.
No-Regret Learning in Unknown Games with Correlated Payoffs
We consider the problem of learning to play a repeated multi-agent game with an unknown reward function.
Noise Regularization for Conditional Density Estimation
To address this issue, we develop a model-agnostic noise regularization method for CDE that adds random perturbations to the data during training.
Structured Variational Inference in Unstable Gaussian Process State Space Models
Finally, we show experimentally that our learning algorithm performs well in stable and unstable real systems with hidden states.
Mixed-Variable Bayesian Optimization
However, few methods exist for mixed-variable domains and none of them can handle discrete constraints that arise in many real-world applications.
Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning
Furthermore, this successful attempt paves the way for further use at different levels of HVAC systems, with promising energy, operational, and commissioning costs savings, and it is a practical demonstration of the positive effects that Artificial Intelligence can have on environmental sustainability.
Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning
We evaluate the resulting algorithm to safely explore the dynamics of an inverted pendulum and to solve a reinforcement learning task on a cart-pole system with safety constraints.
Stochastic Bandits with Context Distributions
We introduce a stochastic contextual bandit model where at each time step the environment chooses a distribution over a context set and samples the context from this distribution.
Learning Generative Models across Incomparable Spaces
Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety.
Evaluating GANs via Duality
Generative Adversarial Networks (GANs) have shown great results in accurately modeling complex distributions, but their training is known to be difficult due to instabilities caused by a challenging minimax optimization problem.
Online Variance Reduction with Mixtures
Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction.
AReS and MaRS - Adversarial and MMD-Minimizing Regression for SDEs
Stochastic differential equations are an important modeling class in many disciplines.
Multi-Player Bandits: The Adversarial Case
We consider a setting where multiple players sequentially choose among a common set of actions (arms).
ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems
Parameter inference in ordinary differential equations is an important problem in many applied sciences and in engineering, especially in a data-scarce setting.
Adaptive Sequence Submodularity
In many machine learning applications, one needs to interactively select a sequence of items (e. g., recommending movies based on a user's feedback) or make sequential decisions in a certain order (e. g., guiding an agent through a series of states).
Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces
In order to scale the method and keep its benefits, we propose an algorithm (LineBO) that restricts the problem to a sequence of iteratively chosen one-dimensional sub-problems that can be solved efficiently.
No-Regret Bayesian Optimization with Unknown Hyperparameters
In this paper, we present the first BO algorithm that is provably no-regret and converges to the optimum without knowledge of the hyperparameters.
Information-Directed Exploration for Deep Reinforcement Learning
Efficient exploration remains a major challenge for reinforcement learning.
Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features
We develop an efficient and provably no-regret Bayesian optimization (BO) algorithm for optimization of black-box functions in high dimensions.
Provable Variational Inference for Constrained Log-Submodular Models
Submodular maximization problems appear in several areas of machine learning and data science, as many useful modelling concepts such as diversity and coverage satisfy this natural diminishing returns property.
A domain agnostic measure for monitoring and evaluating GANs
Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring the progress of a single model throughout training.
Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy
In this paper, we present a deep learning approach that uses images of the sky to compensate power fluctuations predictively and reduces battery stress.
A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity
In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness.
The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
We demonstrate our method by learning the safe region of attraction for a simulated inverted pendulum.
Discrete Sampling using Semigradient-based Product Mixtures
We consider the problem of inference in discrete probabilistic models, that is, distributions over subsets of a finite ground set.
Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations
To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the overall estimation error.
Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making
We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations.
Teaching Multiple Concepts to a Forgetful Learner
Our framework is both generic, allowing the design of teaching schedules for different memory models, and also interactive, allowing the teacher to adapt the schedule to the underlying forgetting mechanisms of the learner.
Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference
Mean field inference in probabilistic models is generally a highly nonconvex problem.
Fast Gaussian Process Based Gradient Matching for Parameter Identification in Systems of Nonlinear ODEs
Parameter identification and comparison of dynamical systems is a challenging task in many fields.
Learning-based Model Predictive Control for Safe Exploration
However, these methods typically do not provide any safety guarantees, which prevents their use in safety-critical, real-world applications.
Online Variance Reduction for Stochastic Optimization
Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data.
Information Directed Sampling and Bandits with Heteroscedastic Noise
In the stochastic bandit problem, the goal is to maximize an unknown function via a sequence of noisy evaluations.
Differentiable Learning of Submodular Models
In this paper we focus on the problem of submodular minimization, for which we show that such layers are indeed possible.
Interactive Submodular Bandit
We then receive a noisy feedback about the utility of the action (e. g., ratings) which we model as a submodular function over the context-action space.
Fake News Detection in Social Networks via Crowd Signals
The main objective of our work is to minimize the spread of misinformation by stopping the propagation of fake news in the network.
Social and Information Networks
Learning User Preferences to Incentivize Exploration in the Sharing Economy
We provide formal guarantees on the performance of our algorithm and test the viability of our approach in a user study with data of apartments on Airbnb.
Stochastic Submodular Maximization: The Case of Coverage Functions
By exploiting that common extensions act linearly on the class of submodular functions, we employ projected stochastic gradient ascent and its variants in the continuous domain, and perform rounding to obtain discrete solutions.
Continuous DR-submodular Maximization: Structure and Algorithms
Concretely, we first devise a "two-phase" algorithm with $1/4$ approximation guarantee.
Learning Implicit Generative Models Using Differentiable Graph Tests
Recently, there has been a growing interest in the problem of learning rich implicit models - those from which we can sample, but can not evaluate their density.
Probabilistic Submodular Maximization in Sub-Linear Time
As a remedy, we introduce the problem of sublinear time probabilistic submodular maximization: Given training examples of functions (e. g., via user feature vectors), we seek to reduce the ground set so that optimizing new functions drawn from the same distribution will provide almost as much value when restricted to the reduced ground set as when using the full set.
Distributed and Provably Good Seedings for k-Means in Constant Rounds
The k-Means++ algorithm is the state of the art algorithm to solve k-Means clustering problems as the computed clusterings are O(log k) competitive in expectation.
Deletion-Robust Submodular Maximization: Data Summarization with "the Right to be Forgotten"
How can we summarize a dynamic data stream when elements selected for the summary can be deleted at any time?
Uniform Deviation Bounds for k-Means Clustering
In this paper, we provide a novel framework to obtain uniform deviation bounds for loss functions which are unbounded.
Differentially Private Submodular Maximization: Data Summarization in Disguise
Many data summarization applications are captured by the general framework of submodular maximization.
Streaming Non-monotone Submodular Maximization: Personalized Video Summarization on the Fly
The need for real time analysis of rapidly producing data streams (e. g., video and image streams) motivated the design of streaming algorithms that can efficiently extract and summarize useful information from massive data "on the fly".
Data Structures and Algorithms Information Retrieval
An Online Learning Approach to Generative Adversarial Networks
We consider the problem of training generative models with a Generative Adversarial Network (GAN).
Safe Model-based Reinforcement Learning with Stability Guarantees
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data.
Model-based Reinforcement Learning
reinforcement-learning
+1
Training Gaussian Mixture Models at Scale via Coresets
In this work we show how to construct coresets for mixtures of Gaussians.
Practical Coreset Constructions for Machine Learning
We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set.
Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting
We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes.
Guarantees for Greedy Maximization of Non-submodular Functions with Applications
Our guarantees are characterized by a combination of the (generalized) curvature $\alpha$ and the submodularity ratio $\gamma$.
Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
In practice, the parameters of control policies are often tuned manually.
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means
In this paper, we provide a novel framework to obtain uniform deviation bounds for loss functions which are *unbounded*.
Scalable k-Means Clustering via Lightweight Coresets
As such, they have been successfully used to scale up clustering models to massive data sets.
Learning to Use Learners' Advice
In our setting, the feedback at any time $t$ is limited in a sense that it is only available to the expert $i^t$ that has been selected by the central algorithm (forecaster), \emph{i. e.}, only the expert $i^t$ receives feedback from the environment and gets to learn at time $t$.
Coordinated Online Learning With Applications to Learning User Preferences
We study an online multi-task learning setting, in which instances of related tasks arrive sequentially, and are handled by task-specific online learners.
Variational Inference in Mixed Probabilistic Submodular Models
We consider the problem of variational inference in probabilistic models with both log-submodular and log-supermodular higher-order potentials.
Cooperative Graphical Models
We study a rich family of distributions that capture variable interactions significantly more expressive than those representable with low-treewidth or pairwise graphical models, or log-supermodular models.
Fast and Provably Good Seedings for k-Means
Seeding - the task of finding initial cluster centers - is critical in obtaining high-quality clusterings for k-Means.
Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
We present a new algorithm, truncated variance reduction (TruVaR), that treats Bayesian optimization (BO) and level-set estimation (LSE) with Gaussian processes in a unified fashion.
Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
Submodular continuous functions are a category of (generally) non-convex/non-concave functions with a wide spectrum of applications.
Safe Exploration in Finite Markov Decision Processes with Gaussian Processes
We define safety in terms of an, a priori unknown, safety constraint that depends on states and actions.
Horizontally Scalable Submodular Maximization
A variety of large-scale machine learning problems can be cast as instances of constrained submodular maximization.
Near-optimal Bayesian Active Learning with Correlated and Noisy Tests
We consider the Bayesian active learning and experimental design problem, where the goal is to learn the value of some unknown target variable through a sequence of informative, noisy tests.
Actively Learning Hemimetrics with Applications to Eliciting User Preferences
We propose an active learning algorithm that substantially reduces this sample complexity by exploiting the structural constraints on the version space of hemimetrics.