Search Results for author:
Found 51 papers, 12 papers with code
Doubly Robust Structure Identification from Temporal Data
Furthermore, potential causes may be correlated in practical applications.
Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers
We perform instruction optimization for ChatGPT and use extensive experiments to show that our INSTINCT consistently outperforms the existing methods in different tasks, such as in various instruction induction tasks and the task of improving the zero-shot chain-of-thought instruction.
Online Resource Allocation with Convex-set Machine-Learned Advice
Specifically, in a C-Pareto optimal setting, we maximize the robust ratio while ensuring that the consistent ratio is at least C. Our proposed C-Pareto optimal algorithm is an adaptive protection level algorithm, which extends the classical fixed protection level algorithm introduced in Littlewood (2005) and Ball and Queyranne (2009).
Memory-Constrained Algorithms for Convex Optimization via Recursive Cutting-Planes
We propose a family of recursive cutting-plane algorithms to solve feasibility problems with constrained memory, which can also be used for first-order convex optimization.
DRCFS: Doubly Robust Causal Feature Selection
Knowing the features of a complex system that are highly relevant to a particular target variable is of fundamental interest in many areas of science.
Effective Dimension in Bandit Problems under Censorship
In this paper, we study both multi-armed and contextual bandit problems in censored environments.
Adversarial Rewards in Universal Learning for Contextual Bandits
We show that optimistic universal learning for contextual bandits with adversarial rewards is impossible in general, contrary to all previously studied settings in online learning -- including standard supervised learning.
Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal
For the feasibility problem, in which an algorithm only has access to a separation oracle, we show a stronger trade-off: for at most $d^{2-\delta}$ memory, the number of queries required is $\tilde\Omega(d^{1+\delta})$.
Multi-channel Autobidding with Budget and ROI Constraints
In light of this finding, under a bandit feedback setting that mimics real-world scenarios where advertisers have limited information on ad auctions in each channels and how channels procure ads, we present an efficient learning algorithm that produces per-channel budgets whose resulting conversion approximates that of the global optimal problem.
Contextual Bandits and Optimistically Universal Learning
Lastly, we consider the case of added continuity assumptions on rewards and show that these lead to universal consistency for significantly larger classes of data-generating processes.
Sample-Then-Optimize Batch Neural Thompson Sampling
linear model), which is equivalently sampled from the GP posterior with the NTK as the kernel function.
Weighted Maximum Entropy Inverse Reinforcement Learning
We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories.
On Provably Robust Meta-Bayesian Optimization
We prove that both algorithms are asymptotically no-regret even when some or all previous tasks are dissimilar to the current task, and show that RM-GP-UCB enjoys a better theoretical robustness than RM-GP-TS.
Federated Neural Bandits
To better exploit the federated setting, FN-UCB adopts a weighted combination of two UCBs: $\text{UCB}^{a}$ allows every agent to additionally use the observations from the other agents to accelerate exploration (without sharing raw observations), while $\text{UCB}^{b}$ uses an NN with aggregated parameters for reward prediction in a similar way to federated averaging for supervised learning.
Universal Regression with Adversarial Responses
In addition, our analysis also provides a learning rule for mean estimation in general metric spaces that is consistent under adversarial responses without any moment conditions on the sequence, a result of independent interest.
Rectified Max-Value Entropy Search for Bayesian Optimization
Although the existing max-value entropy search (MES) is based on the widely celebrated notion of mutual information, its empirical performance can suffer due to two misconceptions whose implications on the exploration-exploitation trade-off are investigated in this paper.
Robust Entropy-regularized Markov Decision Processes
Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications.
Optimizing Conditional Value-At-Risk of Black-Box Functions
This paper presents two Bayesian optimization (BO) algorithms with theoretical performance guarantee to maximize the conditional value-at-risk (CVaR) of a black-box function: CV-UCB and CV-TS which are based on the well-established principle of optimism in the face of uncertainty and Thompson sampling, respectively.
Differentially Private Federated Bayesian Optimization with Distributed Exploration
The resulting differentially private FTS with DE (DP-FTS-DE) algorithm is endowed with theoretical guarantees for both the privacy and utility and is amenable to interesting theoretical insights about the privacy-utility trade-off.
Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization
Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function.
Value-at-Risk Optimization with Gaussian Processes
Value-at-risk (VaR) is an established measure to assess risks in critical real-world applications with random environmental factors.
Convolutional Normalizing Flows for Deep Gaussian Processes
Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart.
Top-$k$ Ranking Bayesian Optimization
This paper presents a novel approach to top-$k$ ranking Bayesian optimization (top-$k$ ranking BO) which is a practical and significant generalization of preferential BO to handle top-$k$ ranking and tie/indifference observations.
An Information-Theoretic Framework for Unifying Active Learning Problems
This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant.
Variational Bayesian Unlearning
We frame this problem as one of minimizing the Kullback-Leibler divergence between the approximate posterior belief of model parameters after directly unlearning from erased data vs. the exact posterior belief from retraining with remaining data.
Federated Bayesian Optimization via Thompson Sampling
Bayesian optimization (BO) is a prominent approach to optimizing expensive-to-evaluate black-box functions.
Competitive Ratios for Online Multi-capacity Ridesharing
The desired matching between resources and request groups is constrained by the edges between requests and request groups in this tripartite graph (i. e., a request can be part of at most one request group in the final assignment).
Zone pAth Construction (ZAC) based Approaches for Effective Real-Time Ridesharing
This challenge has been addressed in existing work by: (i) generating as many relevant feasible (with respect to the available delay for customers) combinations of requests as possible in real-time; and then (ii) optimizing assignment of the feasible request combinations to vehicles.
A Relation Analysis of Markov Decision Process Frameworks
We show that the entropy-regularized MDP is equivalent to a stochastic MDP model, and is strictly subsumed by the general regularized MDP.
Learning Structure in Nested Logit Models
We formulate the problem of learning an optimal nesting structure from the data as a mixed integer nonlinear programming (MINLP) optimization problem and solve it using a variant of the linear outer approximation algorithm.
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
This paper presents a recursive reasoning formalism of Bayesian optimization (BO) to model the reasoning process in the interactions between boundedly rational, self-interested agents with unknown, complex, and costly-to-evaluate payoff functions in repeated games, which we call Recursive Reasoning-Based BO (R2-B2).
Inverse Reinforcement Learning with Missing Data
We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories.
Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL).
Incentive-aware Contextual Pricing with Non-parametric Market Noise
We show that this design allows the seller to control the number of periods in which buyers significantly corrupt their bids.
Implicit Posterior Variational Inference for Deep Gaussian Processes
This paper presents an implicit posterior variational inference (IPVI) framework for DGPs that can ideally recover an unbiased posterior belief and still preserve time efficiency.
Optimal Explanations of Linear Models
We propose a general optimization framework to create explanations for linear models.
The Price of Interpretability
When quantitative models are used to support decision-making on complex and important topics, understanding a model's ``reasoning'' can increase trust in its predictions, expose hidden biases, or reduce vulnerability to adversarial attacks.
Maximum Weight Online Matching with Deadlines
We study the problem of matching agents who arrive at a marketplace over time and leave after d time periods.
Data Structures and Algorithms
Real-Time Bidding with Side Information
We consider the problem of repeated bidding in online advertising auctions when some side information (e. g. browser cookies) is available ahead of submitting a bid in the form of a $d$-dimensional vector.
Online Learning with a Hint
We show that the player can benefit from such a hint if the set of feasible actions is sufficiently round.
Stochastic Variational Inference for Bayesian Sparse Gaussian Process Regression
This paper presents a novel variational inference framework for deriving a family of Bayesian sparse Gaussian process regression (SGPR) models whose approximations are variationally optimal with respect to the full-rank GPR model enriched with various corresponding correlation structures of the observation noises.
Structured Prediction by Conditional Risk Minimization
We propose a general approach for supervised learning with structured output spaces, such as combinatorial and polyhedral sets, that is based on minimizing estimated conditional risk functions.
Solving Combinatorial Games using Products, Projections and Lexicographically Optimal Bases
We give a general recipe to simulate the multiplicative weights update algorithm in time polynomial in their natural dimension.
Inverse Reinforcement Learning with Locally Consistent Reward Functions
By representing our IRL problem with a probabilistic graphical model, an expectation-maximization (EM) algorithm can be devised to iteratively learn the different reward functions and the stochastic transitions between them in order to jointly improve the likelihood of the expert’s demonstrated trajectories.
Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyond
This paper presents a novel nonmyopic adaptive Gaussian process planning (GPP) framework endowed with a general class of Lipschitz continuous reward functions that can unify some active learning/sensing and Bayesian optimization criteria and offer practitioners some flexibility to specify their desired choices for defining new tasks/problems.
No-Regret Learnability for Piecewise Linear Losses
In the convex optimization approach to online regret minimization, many methods have been developed to guarantee a $O(\sqrt{T})$ bound on regret for subdifferentiable convex loss functions with bounded subgradients, by using a reduction to linear loss functions.
Parallel Gaussian Process Regression for Big Data: Low-Rank Representation Meets Markov Approximation
To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that is novel in leveraging the dual computational advantages stemming from complementing a low-rank approximate representation of the full-rank GP based on a support set of inputs with a Markov approximation of the resulting residual process; the latter approximation is guaranteed to be closest in the Kullback-Leibler distance criterion subject to some constraint and is considerably more refined than that of existing sparse GP models utilizing low-rank representations due to its more relaxed conditional independence assumption (especially with larger data).
Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots.
Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability.
Regret based Robust Solutions for Uncertain Markov Decision Processes
Most robust optimization approaches for these problems have focussed on the computation of {\em maximin} policies which maximize the value corresponding to the worst realization of the uncertainty.
Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability.
