
Machine Unlearning via Algorithmic Stability
We study the problem of machine unlearning and identify a notion of algo...
read it

On Convergence and Generalization of Dropout Training
We study dropout in twolayer neural networks with rectified linear unit...
read it

Adversarial Robustness of Supervised Sparse Coding
Several recent results provide theoretical insights into the phenomena o...
read it

FetchSGD: CommunicationEfficient Federated Learning with Sketching
Existing approaches to federated learning suffer from a communication bo...
read it

Is Network the Bottleneck of Distributed Training?
Recently there has been a surge of research on improving the communicati...
read it

Corralling Stochastic Bandit Algorithms
We study the problem of corralling stochastic bandit algorithms, that is...
read it

Dropout: Explicit Forms and Capacity Control
We investigate the capacity control provided by dropout in various machi...
read it

Private Stochastic Convex Optimization: Efficient Algorithms for Nonsmooth Objectives
In this paper, we revisit the problem of private stochastic convex optim...
read it

Multiview Representation Learning for a Union of Subspaces
Canonical correlation analysis (CCA) is a popular technique for learning...
read it

Bandits with Feedback Graphs and Switching Costs
We study the adversarial multiarmed bandit problem where partial observ...
read it

On Dropout and Nuclear Norm Regularization
We give a formal and complete characterization of the explicit regulariz...
read it

Communicationefficient distributed SGD with Sketching
Largescale distributed training of neural networks is often limited by ...
read it

Learning from Multiview Correlations in OpenDomain Videos
An increasing number of datasets contain multiple views, such as video, ...
read it

Policy Regret in Repeated Games
The notion of policy regret in online learning is a well defined? perfor...
read it

Streaming Kernel PCA with Õ(√(n)) Random Features
We study the statistical and computational aspects of kernel principal c...
read it

On the Implicit Bias of Dropout
Algorithmic approaches endow deep learning systems with implicit bias th...
read it

Visual Robot Task Planning
Prospection, the act of predicting the consequences of many possible fut...
read it

Learning to Imagine Manipulation Goals for Robot Task Planning
Prospection is an important part of how humans come up with new task pla...
read it

Stochastic Approximation for Canonical Correlation Analysis
We study canonical correlation analysis (CCA) as a stochastic optimizati...
read it

Deep Generalized Canonical Correlation Analysis
We present Deep Generalized Canonical Correlation Analysis (DGCCA)  a ...
read it

Symmetry, Saddle Points, and Global Geometry of Nonconvex Matrix Factorization
We propose a general theory for studying the geometry of nonconvex objec...
read it

Understanding Deep Neural Networks with Rectified Linear Units
In this paper we investigate the family of functions representable by de...
read it

On Faster Convergence of Cyclic Block Coordinate Descenttype Methods for Strongly Convex Minimization
The cyclic block coordinate descenttype (CBCDtype) methods, which perf...
read it

Disease Trajectory Maps
Medical researchers are coming to appreciate that many diseases are in f...
read it

A First Order Free Lunch for SQRTLasso
Many statistical machine learning techniques sacrifice convenient comput...
read it

Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction
We propose a stochastic variance reduced optimization algorithm for solv...
read it

Embedding Lexical Features via LowRank Tensors
Modern NLP models rely heavily on engineered features, which often combi...
read it

Stochastic Optimization of PCA with Capped MSG
We study PCA as a stochastic optimization problem and propose a novel st...
read it

Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
Online learning algorithms are designed to learn even when their input i...
read it