Search Results for author:
Found 56 papers, 12 papers with code
Communication-Efficient Federated Learning with Sketching
A key insight in the design of FedSketchedSGD is that, because the Count Sketch is linear, momentum and error accumulation can both be carried out within the sketch.
On The Statistical Complexity of Offline Decision-Making
We study the statistical complexity of offline decision-making with function approximation, establishing (near) minimax-optimal rates for stochastic contextual bandits and Markov decision processes.
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
We study learning in a dynamically evolving environment modeled as a Markov game between a learner and a strategic opponent that can adapt to the learner's strategies.
Offline Multitask Representation Learning for Reinforcement Learning
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation.
Public-data Assisted Private Stochastic Optimization: Power and Limitations
We also study PA-DP supervised learning with \textit{unlabeled} public samples.
DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation
To address this challenge, we first establish a generalization bound for the adversarial target loss, which consists of (i) terms related to the loss on the data, and (ii) a measure of worst-case domain divergence.
On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond
This result is surprising, given that the prior work suggested an unfavorable sample complexity of the RO-based algorithm compared to the VS-based algorithm, whereas posterior sampling is rarely considered in offline RL due to its explorative nature.
Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates
We further show that, without assuming the KL condition, the same gradient descent algorithm can achieve fast convergence to a stationary point when the gradient stays sufficiently large during the run of the algorithm.
From Adaptive Query Release to Machine Unlearning
We give efficient unlearning algorithms for linear and prefix-sum query classes.
VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
We corroborate the statistical and computational efficiency of VIPeR with an empirical evaluation on a wide set of synthetic and real-world datasets.
On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
To the best of our knowledge, these are the first $\tilde{\mathcal{O}}(\frac{1}{K})$ bound and absolute zero sub-optimality bound respectively for offline RL with linear function approximation from adaptive data with partial coverage.
A Risk-Sensitive Approach to Policy Optimization
Without cost constraints, we find that pessimistic risk profiles can be used to reduce cost while improving total reward accumulation.
Adversarial Robustness is at Odds with Lazy Training
Recent works show that adversarial examples exist for random neural networks [Daniely and Schacham, 2020] and that these examples can be found using a single step of gradient ascent [Bubeck et al., 2021].
Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
We provide a new efficient algorithm that finds an $\tilde{O}\big(\big[\frac{\sqrt{d}}{n\varepsilon}\big]^{2/3}\big)$-stationary point in the finite-sum setting, where $n$ is the number of samples.
Differentially Private Generalized Linear Models Revisited
For this case, we close the gap in the existing work and show that the optimal rate is (up to log factors) $\Theta\left(\frac{\Vert w^*\Vert}{\sqrt{n}} + \min\left\{\frac{\Vert w^*\Vert}{\sqrt{n\epsilon}},\frac{\sqrt{\text{rank}}\Vert w^*\Vert}{n\epsilon}\right\}\right)$, where $\text{rank}$ is the rank of the design matrix.
A Risk-Sensitive Policy Gradient Method
Standard deep reinforcement learning (DRL) agents aim to maximize expected reward, considering collected experiences equally in formulating a policy.
Machine Unlearning via Algorithmic Stability
Our key contribution is the design of corresponding efficient unlearning algorithms, which are based on constructing a (maximal) coupling of Markov chains for the noisy SGD procedure.
On Convergence and Generalization of Dropout Training
We study dropout in two-layer neural networks with rectified linear unit (ReLU) activations.
Adversarial Robustness of Supervised Sparse Coding
Several recent results provide theoretical insights into the phenomena of adversarial examples.
FetchSGD: Communication-Efficient Federated Learning with Sketching
A key insight in the design of FetchSGD is that, because the Count Sketch is linear, momentum and error accumulation can both be carried out within the sketch.
Is Network the Bottleneck of Distributed Training?
As such, we advocate that the real challenge of distributed training is for the network community to develop high-performance network transport to fully utilize the network capacity and achieve linear scale-out.
Corralling Stochastic Bandit Algorithms
We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm.
Dropout: Explicit Forms and Capacity Control
In deep learning, we show that the data-dependent regularizer due to dropout directly controls the Rademacher complexity of the underlying class of deep neural networks.
Private Stochastic Convex Optimization: Efficient Algorithms for Non-smooth Objectives
In this paper, we revisit the problem of private stochastic convex optimization.
Multiview Representation Learning for a Union of Subspaces
Canonical correlation analysis (CCA) is a popular technique for learning representations that are maximally correlated across multiple views in data.
Efficient Convex Relaxations for Streaming PCA
We revisit two algorithms, matrix stochastic gradient (MSG) and $\ell_2$-regularized MSG (RMSG), that are instances of stochastic gradient descent (SGD) on a convex relaxation to principal component analysis (PCA).
On Differentially Private Graph Sparsification and Applications
In this paper, we study private sparsification of graphs.
Bandits with Feedback Graphs and Switching Costs
We give a new algorithm whose regret guarantee depends only on the domination number of the graph.
On Dropout and Nuclear Norm Regularization
We give a formal and complete characterization of the explicit regularizer induced by dropout in deep linear networks with squared loss.
Communication-efficient distributed SGD with Sketching
Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time.
Streaming Kernel PCA with \tilde{O}(\sqrt{n}) Random Features
We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, $O(\sqrt{n} \log n)$ features suffices to achieve $O(1/\epsilon^2)$ sample complexity.
Differentially Private Robust Low-Rank Approximation
In this paper, we study the following robust low-rank matrix approximation problem: given a matrix $A \in \R^{n \times d}$, find a rank-$k$ matrix $B$, while satisfying differential privacy, such that $ \norm{ A - B }_p \leq \alpha \mathsf{OPT}_k(A) + \tau,$ where $\norm{ M }_p$ is the entry-wise $\ell_p$-norm and $\mathsf{OPT}_k(A):=\min_{\mathsf{rank}(X) \leq k} \norm{ A - X}_p$.
Learning from Multiview Correlations in Open-Domain Videos
This shows it is possible to learn reliable representations across disparate, unaligned and noisy modalities, and encourages using the proposed approach on larger datasets.
Policy Regret in Repeated Games
We revisit the notion of policy regret and first show that there are online learning settings in which policy regret and external regret are incompatible: any sequence of play that achieves a favorable regret with respect to one definition must do poorly with respect to the other.
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features
We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, $O(\sqrt{n} \log n)$ features suffices to achieve $O(1/\epsilon^2)$ sample complexity.
Streaming Principal Component Analysis in Noisy Setting
We study streaming algorithms for principal component analysis (PCA) in noisy settings.
Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization
We revisit convex relaxation based methods for stochastic optimization of principal component analysis (PCA).
On the Implicit Bias of Dropout
Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings.
Visual Robot Task Planning
In this work, we propose a neural network architecture and associated planning algorithm that (1) learns a representation of the world useful for generating prospective futures after the application of high-level actions, (2) uses this generative model to simulate the result of sequences of high-level actions in a variety of environments, and (3) uses this same representation to evaluate these actions and perform tree search to find a sequence of high-level actions in a new environment.
Learning to Imagine Manipulation Goals for Robot Task Planning
Ideally, we would combine the ability of machine learning to leverage big data for learning the semantics of a task, while using techniques from task planning to reliably generalize to new environment.
Stochastic Approximation for Canonical Correlation Analysis
We propose novel first-order stochastic approximation algorithms for canonical correlation analysis (CCA).
Deep Generalized Canonical Correlation Analysis
We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other.
Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e. g., low-rank matrix factorization, phase retrieval, and deep linear neural networks)}.
Understanding Deep Neural Networks with Rectified Linear Units
In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU).
On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
In particular, we first show that for a family of quadratic minimization problems, the iteration complexity $\mathcal{O}(\log^2(p)\cdot\log(1/\epsilon))$ of the CBCD-type methods matches that of the GD methods in term of dependency on $p$, up to a $\log^2 p$ factor.
Disease Trajectory Maps
To answer these questions, we propose the Disease Trajectory Map (DTM), a novel probabilistic model that learns low-dimensional representations of sparse and irregularly sampled time series.
On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About Its Nonsmooth Loss Function
Many machine learning techniques sacrifice convenient computational structures to gain estimation robustness and modeling flexibility.
Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction
We propose a stochastic variance reduced optimization algorithm for solving sparse learning problems with cardinality constraints.
Embedding Lexical Features via Low-Rank Tensors
Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features.
On Deep Multi-View Representation Learning: Objectives and Optimization
We consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for learning while only one view is available for downstream tasks.
Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations
Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains.
Accelerated Mini-batch Randomized Block Coordinate Descent Method
When the regularization function is block separable, we can solve the minimization problems in a randomized block coordinate descent (RBCD) manner.
Stochastic Optimization of PCA with Capped MSG
We study PCA as a stochastic optimization problem and propose a novel stochastic approximation algorithm which we refer to as "Matrix Stochastic Gradient" (MSG), as well as a practical variant, Capped MSG.
