research
∙
02/08/2022
The Lifecycle of a Statistical Model: Model Failure Detection, Identification, and Refitting
The statistical machine learning community has demonstrated considerable...
share
research
∙
01/07/2021
Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization
We extend the Approximate-Proximal Point (aProx) family of model-based m...
research
∙
10/12/2020
Large-Scale Methods for Distributionally Robust Optimization
We propose and analyze algorithms for distributionally robust optimizati...
research
∙
08/10/2020
Robust Validation: Confident Predictions Even When Distributions Shift
While the traditional viewpoint in machine learning and statistics assum...
research
∙
06/24/2020
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations
We design an algorithm which finds an ϵ-approximate stationary point (wi...
research
∙
05/16/2020
Near Instance-Optimality in Differential Privacy
We develop two notions of instance optimality in differential privacy, i...
research
∙
12/05/2019
Lower Bounds for Non-Convex Stochastic Optimization
We lower bound the complexity of finding ϵ-stationary points (with gradi...
research
∙
09/23/2019
Necessary and Sufficient Conditions for Adaptive, Mirror, and Standard Gradient Methods
We study the impact of the constraint set and gradient geometry on the c...
research
∙
06/14/2019
Adversarial Training Can Hurt Generalization
While adversarial training can improve robust accuracy (against an adver...
research
∙
05/31/2019
Unlabeled Data Improves Adversarial Robustness
We demonstrate, theoretically and empirically, that adversarial robustne...
research
∙
03/20/2019
The importance of better models in stochastic optimization
Standard stochastic optimization methods are brittle, sensitive to steps...
research
∙
03/07/2019
A Rank-1 Sketch for Matrix Multiplicative Weights
We show that a simple randomized sketch of the matrix multiplicative wei...
research
∙
01/10/2019
Mean Estimation from One-Bit Measurements
We consider the problem of estimating the mean of a symmetric log-concav...
research
∙
06/14/2018
The Right Complexity Measure in Locally Private Estimation: It is not the Fisher Information
We identify fundamental tradeoffs between statistical utility and privac...
research
∙
04/22/2018
A constrained risk inequality for general losses
We provide a general constrained risk inequality that applies to arbitra...
research
∙
04/11/2018
Derivative free optimization via repeated classification
We develop an algorithm for minimizing a function using n batched functi...
research
∙
11/06/2017
Unsupervised Transformation Learning via Convex Relaxations
Our goal is to extract meaningful transformations from raw images, such ...
research
∙
08/04/2015
Asynchronous stochastic convex optimization
We show that asymptotically, completely asynchronous stochastic gradient...
research
∙
12/07/2013
Optimal rates for zero-order convex optimization: the power of two function evaluations
We consider derivative-free algorithms for stochastic and non-stochastic...
research
∙
05/22/2013
Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
We establish optimal convergence rates for a decomposition-based scalabl...
research
∙
10/07/2012
Privacy Aware Learning
We study statistical risk minimization problems under a privacy model in...
research
∙
09/19/2012
Comunication-Efficient Algorithms for Statistical Optimization
We analyze two communication-efficient algorithms for distributed statis...
research
∙
08/01/2012
Oracle inequalities for computationally adaptive model selection
We analyze general model selection procedures using penalized empirical ...
research
∙
04/07/2012
The asymptotics of ranking algorithms
We consider the predictive problem of supervised ranking, where the task...
research
∙
10/11/2011
The Generalization Ability of Online Algorithms for Dependent Data
We study the generalization performance of online learning algorithms tr...
research
∙
05/24/2011
Ergodic Mirror Descent
We generalize stochastic subgradient descent methods to situations in wh...
research
∙
04/28/2011
Distributed Delayed Stochastic Optimization
We analyze the convergence of gradient-based optimization algorithms tha...
research
∙
03/22/2011