
Accelerated, Optimal, and Parallel: Some Results on ModelBased Stochastic Optimization
We extend the ApproximateProximal Point (aProx) family of modelbased m...
read it

LargeScale Methods for Distributionally Robust Optimization
We propose and analyze algorithms for distributionally robust optimizati...
read it

Robust Validation: Confident Predictions Even When Distributions Shift
While the traditional viewpoint in machine learning and statistics assum...
read it

SecondOrder Information in NonConvex Stochastic Optimization: Power and Limitations
We design an algorithm which finds an ϵapproximate stationary point (wi...
read it

Near InstanceOptimality in Differential Privacy
We develop two notions of instance optimality in differential privacy, i...
read it

Lower Bounds for NonConvex Stochastic Optimization
We lower bound the complexity of finding ϵstationary points (with gradi...
read it

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...
read it

Adversarial Training Can Hurt Generalization
While adversarial training can improve robust accuracy (against an adver...
read it

Unlabeled Data Improves Adversarial Robustness
We demonstrate, theoretically and empirically, that adversarial robustne...
read it

The importance of better models in stochastic optimization
Standard stochastic optimization methods are brittle, sensitive to steps...
read it

A Rank1 Sketch for Matrix Multiplicative Weights
We show that a simple randomized sketch of the matrix multiplicative wei...
read it

Mean Estimation from OneBit Measurements
We consider the problem of estimating the mean of a symmetric logconcav...
read it

The Right Complexity Measure in Locally Private Estimation: It is not the Fisher Information
We identify fundamental tradeoffs between statistical utility and privac...
read it

A constrained risk inequality for general losses
We provide a general constrained risk inequality that applies to arbitra...
read it

Derivative free optimization via repeated classification
We develop an algorithm for minimizing a function using n batched functi...
read it

Unsupervised Transformation Learning via Convex Relaxations
Our goal is to extract meaningful transformations from raw images, such ...
read it

Asynchronous stochastic convex optimization
We show that asymptotically, completely asynchronous stochastic gradient...
read it

Optimal rates for zeroorder convex optimization: the power of two function evaluations
We consider derivativefree algorithms for stochastic and nonstochastic...
read it

Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
We establish optimal convergence rates for a decompositionbased scalabl...
read it

Privacy Aware Learning
We study statistical risk minimization problems under a privacy model in...
read it

ComunicationEfficient Algorithms for Statistical Optimization
We analyze two communicationefficient algorithms for distributed statis...
read it

Oracle inequalities for computationally adaptive model selection
We analyze general model selection procedures using penalized empirical ...
read it

The asymptotics of ranking algorithms
We consider the predictive problem of supervised ranking, where the task...
read it

The Generalization Ability of Online Algorithms for Dependent Data
We study the generalization performance of online learning algorithms tr...
read it

Ergodic Mirror Descent
We generalize stochastic subgradient descent methods to situations in wh...
read it

Distributed Delayed Stochastic Optimization
We analyze the convergence of gradientbased optimization algorithms tha...
read it

Randomized Smoothing for Stochastic Optimization
We analyze convergence rates of stochastic optimization procedures for n...
read it
John C. Duchi
is this you? claim profile
Assistant professor of Statistics and Electrical Engineering at Stanford University.