Search Results for author:
Found 70 papers, 18 papers with code
Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity
We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem.
Demystifying Disagreement-on-the-Line in High Dimensions
Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain.
Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
In large-scale machine learning, recent works have studied the effects of compressing gradients in stochastic optimization in order to alleviate the communication bottleneck.
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods
Autoencoders are a popular model in many branches of machine learning and lossy data compression.
Probable Domain Generalization via Quantile Risk Minimization
By minimizing the $\alpha$-quantile of predictor's risk distribution over domains, QRM seeks predictors that perform well with probability $\alpha$.
Toward Certified Robustness Against Real-World Distribution Shifts
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.
Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds
We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret.
Straggler-Resilient Personalized Federated Learning
Federated Learning is an emerging learning paradigm that allows training models from samples distributed across a large network of clients while respecting privacy and communication restrictions.
Self-Consistency of the Fokker-Planck Equation
In this paper, we exploit this concept to design a potential function of the hypothesis velocity fields, and prove that, if such a function diminishes to zero during the training procedure, the trajectory of the densities generated by the hypothesis velocity fields converges to the solution of the FPE in the Wasserstein-2 sense.
Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints
In modern machine learning, users often have to collaborate to learn the distribution of the data.
FedAvg with Fine Tuning: Local Updates Lead to Representation Learning
We show that the reason behind generalizability of the FedAvg's output is its power in learning the common data representation among the clients' tasks, by leveraging the diversity among client data distributions via local updates.
Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents
Recent years have witnessed a growing interest in the topic of min-max optimization, owing to its relevance in the context of generative adversarial networks (GANs), robust control and optimization, and reinforcement learning.
Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Coding
Motivated by the empirical success of deep neural network (DNN) compressors on large, real-world data, we investigate methods to estimate the rate-distortion function on such data, which would allow comparison of DNN compressors with optimality.
Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data.
Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control
Though this fundamental tradeoff between nominal performance and robustness is known to exist, it is not well-characterized in quantitative terms.
Do Deep Networks Transfer Invariances Across Classes?
Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks.
Ranked #16 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Binary Classification Under $\ell_0$ Attacks for General Noise Distribution
We introduce a classification method which employs a nonlinear component called truncation, and show in an asymptotic scenario, as long as the adversary is restricted to perturb no more than $\sqrt{d}$ data samples, we can almost achieve the optimal classification error in the absence of the adversary, i. e. we can completely neutralize adversary's effect.
T-Cal: An optimal test for the calibration of predictive models
We find that detecting mis-calibration is only possible when the conditional probabilities of the classes are sufficiently smooth functions of the predictions.
Linear Stochastic Bandits over a Bit-Constrained Channel
Specifically, in our setup, an agent interacting with an environment transmits encoded estimates of an unknown model parameter to a server over a communication channel of finite capacity.
What Functions Can Graph Neural Networks Generate?
We prove that: (i) a GNN, as a graph function, is necessarily permutation compatible; (ii) conversely, any permutation compatible function, when restricted on input graphs with distinct node features, can be generated by a GNN; (iii) for arbitrary node features (not necessarily distinct), a simple feature augmentation scheme suffices to generate a permutation compatible function by a GNN; (iv) permutation compatibility can be verified by checking only quadratically many functional constraints, rather than an exhaustive search over all the permutations; (v) GNNs can generate \textit{any} graph function once we augment the node features with node identities, thus going beyond graph isomorphism and permutation compatibility.
Probabilistically Robust Learning: Balancing Average- and Worst-case Performance
From a theoretical point of view, this framework overcomes the trade-offs between the performance and the sample-complexity of worst-case and average-case learning.
Efficient and Robust Classification for Sparse Attacks
In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy.
The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
Our developed theory reveals the nontrivial effect of overparametrization on robustness and indicates that for adversarially trained random features models, high overparametrization can hurt robust generalization.
Adversarial Tradeoffs in Robust State Estimation
We provide an algorithm to find this perturbation given data realizations, and develop upper and lower bounds on the adversarial state estimation error in terms of the standard (non-adversarial) estimation error and the spectral properties of the resulting observer.
Minimax Optimization: The Case of Convex-Submodular
Prior literature has thus far mainly focused on studying such problems in the continuous domain, e. g., convex-concave minimax optimization is now understood to a significant extent.
Adversarial Robustness with Semi-Infinite Constrained Learning
In particular, we leverage semi-infinite optimization and non-convex duality theory to show that adversarial training is equivalent to a statistical problem over perturbation distributions, which we characterize completely.
Out-of-Distribution Robustness in Deep Learning Compression
In recent years, deep neural network (DNN) compression systems have proved to be highly effective for designing source codes for many natural sources.
An Agnostic Approach to Federated Learning with Class Imbalance
Federated Learning (FL) has emerged as the tool of choice for training deep models over heterogeneous and decentralized datasets.
Exploiting Heterogeneity in Robust Federated Best-Arm Identification
We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best arm (i. e., the arm with the highest mean reward) with prescribed confidence.
AutoEKF: Scalable System Identification for COVID-19 Forecasting from Large-Scale GPS Data
The likelihood of the observations is estimated recursively using an Extended Kalman Filter and can be easily optimized using gradient-based methods to compute maximum likelihood estimators.
Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model
Under the assumption that data is distributed according to the Gaussian mixture model, our goal is to characterize the optimal robust classifier and the corresponding robust classification error as well as a variety of trade-offs between robustness, accuracy, and the adversary's budget.
Federated Functional Gradient Boosting
First, in the semi-heterogeneous setting, when the marginal distributions of the feature vectors on client machines are identical, we develop the federated functional gradient boosting (FFGB) method that provably converges to the global minimum.
Model-Based Domain Generalization
Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data.
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
We consider a standard federated learning (FL) architecture where a group of clients periodically coordinate with a central server to train a statistical model.
Exploiting Shared Representations for Personalized Federated Learning
Based on this intuition, we propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client.
Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity
Federated Learning is a novel paradigm that involves learning from data samples distributed across a large network of clients while the data remains local.
Sinkhorn Natural Gradient for Generative Models
In this regard, we propose a novel Sinkhorn Natural Gradient (SiNG) algorithm which acts as a steepest descent method on the probability space endowed with the Sinkhorn divergence.
Sinkhorn Barycenter via Functional Gradient Descent
In this paper, we consider the problem of computing the barycenter of a set of probability distributions under the Sinkhorn divergence.
Submodular Meta-Learning
Motivated by this terminology, we propose a novel meta-learning framework in the discrete domain where each task is equivalent to maximizing a set function under a cardinality constraint.
Safe Learning under Uncertain Objectives and Constraints
More precisely, by assuming that Reliable-FW has access to a (stochastic) gradient oracle of the objective function and a noisy feasibility oracle of the safety polytope, it finds an $\epsilon$-approximate first-order stationary point with the optimal ${\mathcal{O}}({1}/{\epsilon^2})$ gradient oracle complexity (resp.
Learning to Track Dynamic Targets in Partially Known Environments
In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration.
Provable tradeoffs in adversarially robust classification
It is well known that machine learning methods can be vulnerable to adversarially-chosen perturbations of their inputs.
Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
Indeed, natural variation such as lighting or weather conditions can significantly degrade the accuracy of trained neural networks, proving that such natural variation presents a significant challenge for deep learning.
Precise Tradeoffs in Adversarial Training for Linear Regression
Furthermore, we precisely characterize the standard/robust accuracy and the corresponding tradeoff achieved by a contemporary mini-max adversarial training approach in a high-dimensional regime where the number of data points and the parameters of the model grow in proportion to each other.
Quantized Decentralized Stochastic Learning over Directed Graphs
We consider a decentralized stochastic learning problem where data points are distributed among computing nodes communicating over a directed graph.
Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match
Concretely, for a monotone and continuous DR-submodular function, \SCGPP achieves a tight $[(1-1/e)\OPT -\epsilon]$ solution while using $O(1/\epsilon^2)$ stochastic gradients and $O(1/\epsilon)$ calls to the linear optimization oracle.
Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback
In this paper, we propose three online algorithms for submodular maximisation.
Learning Q-network for Active Information Acquisition
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors.
One Sample Stochastic Frank-Wolfe
One of the beauties of the projected gradient descent method lies in its rather simple mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its wide-spread use in many machine learning applications.
Optimal Algorithms for Submodular Maximization with Distributed Constraints
Given this distributed setting, we develop Constraint-Distributed Continuous Greedy (CDCG), a message passing algorithm that converges to the tight $(1-1/e)$ approximation factor of the optimum global solution using only local computation and communication.
FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization
Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized.
Robust and Communication-Efficient Collaborative Learning
We consider a decentralized learning problem, where a set of computing nodes aim at solving a non-convex optimization problem collaboratively.
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
The resulting SDP can be adapted to increase either the estimation accuracy (by capturing the interaction between activation functions of different layers) or scalability (by decomposition and parallel implementation).
Stochastic Conditional Gradient++
It is known that this rate is optimal in terms of stochastic gradient evaluations.
Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free
How can we efficiently mitigate the overhead of gradient communications in distributed optimization?
Black Box Submodular Maximization: Discrete and Continuous Settings
In this paper, we consider the problem of black box continuous submodular maximization where we only have access to the function values and no information about the derivatives is provided.
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Building on the success of deep learning, two modern approaches to learn a probability model from the data are Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs).
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.
An Exact Quantized Decentralized Gradient Descent Algorithm
We consider the problem of decentralized consensus optimization, where the sum of $n$ smooth and strongly convex functions are minimized over $n$ distributed agents that form a connected network.
Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization
Further, for a monotone and continuous DR-submodular function and subject to a general convex body constraint, we prove that our proposed method achieves a $((1-1/e)OPT-\eps)$ guarantee with $O(1/\eps^3)$ stochastic gradient computations.
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity
We also propose One-Shot Frank-Wolfe, a simpler algorithm which requires only a single stochastic gradient estimate in each round and achieves an $O(T^{2/3})$ stochastic regret bound for convex and continuous submodular optimization.
Online Continuous Submodular Maximization
For such settings, we then propose an online stochastic gradient ascent algorithm that also achieves a regret bound of $O(\sqrt{T})$ regret, albeit against a weaker $1/2$-approximation to the best feasible solution in hindsight.
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.
Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap
More precisely, for a monotone and continuous DR-submodular function and subject to a \textit{general} convex body constraint, we prove that \alg achieves a $[(1-1/e)\text{OPT} -\eps]$ guarantee (in expectation) with $\mathcal{O}{(1/\eps^3)}$ stochastic gradient computations.
Gradient Methods for Submodular Maximization
Despite the apparent lack of convexity in such functions, we prove that stochastic projected gradient methods can provide strong approximation guarantees for maximizing continuous submodular functions with convex constraints.
Accelerated Dual Learning by Homotopic Initialization
Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning.
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 $t$.
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.
Near-Optimal Active Learning of Halfspaces via Query Synthesis in the Noisy Setting
This problem has recently gained a lot of interest in automated science and adversarial reverse engineering for which only heuristic algorithms are known.
Sampling from Probabilistic Submodular Models
Submodular and supermodular functions have found wide applicability in machine learning, capturing notions such as diversity and regularity, respectively.
