Search Results for author:
Found 34 papers, 8 papers with code
Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
The goal of decentralized optimization over a network is to optimize a global objective formed by a sum of local (possibly nonsmooth) convex functions using only local computation and communication.
Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation
We provide a detailed study of the estimation of probability distributions---discrete and continuous---in a stringent setting in which data is kept private even from the statistician.
Estimation, Optimization, and Parallelism when Data is Sparse
We study stochastic optimization problems when the \emph{data} is sparse, which is in a sense dual to the current understanding of high-dimensional statistical learning and optimization.
Information-theoretic lower bounds for distributed statistical estimation with communication constraints
We establish minimax risk lower bounds for distributed statistical estimation given a budget $B$ of the total number of bits that may be communicated.
Local Minimax Complexity of Stochastic Convex Optimization
The bounds are expressed in terms of a localized and computational analogue of the modulus of continuity that is central to statistical minimax analysis.
Estimation from Indirect Supervision with Linear Moments
In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradient computation.
Variance-based regularization with convex objectives
We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error.
Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach
We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically.
Asymptotic Optimality in Stochastic Optimization
We study local complexity measures for stochastic convex optimization problems, providing a local minimax theory analogous to that of H\'{a}jek and Le Cam for classical statistical problems.
Certifying Some Distributional Robustness with Principled Adversarial Training
Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms.
Generalizing to Unseen Domains via Adversarial Data Augmentation
Only using training data from a single source distribution, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "hard" under the current model.
Learning Models with Uniform Performance via Distributionally Robust Optimization
A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects.
Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing.
Protection Against Reconstruction and Its Applications in Private Federated Learning
In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection.
Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs
We study a family of (potentially non-convex) constrained optimization problems with convex composite structure.
Element Level Differential Privacy: The Right Granularity of Privacy
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases.
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy
In this work, we precisely characterize the effect of augmentation on the standard error in linear regression when the optimal linear predictor has zero standard and robust error.
FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis
Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent environments.
Knowing what you know: valid and validated confidence sets in multiclass and multilabel prediction
We develop conformal prediction methods for constructing valid predictive confidence sets in multiclass and multilabel problems without assumptions on the data generating distribution.
Distributionally Robust Losses for Latent Covariate Mixtures
While modern large-scale datasets often consist of heterogeneous subpopulations -- for example, multiple demographic groups or multiple text corpora -- the standard practice of minimizing average loss fails to guarantee uniformly low losses across all subpopulations.
Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems
Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics.
On Misspecification in Prediction Problems and Robustness via Improper Learning
We study probabilistic prediction games when the underlying model is misspecified, investigating the consequences of predicting using an incorrect parametric model.
Private Adaptive Gradient Methods for Convex Optimization
We study adaptive methods for differentially private convex optimization, proposing and analyzing differentially private variants of a Stochastic Gradient Descent (SGD) algorithm with adaptive stepsizes, as well as the AdaGrad algorithm.
Adapting to Function Difficulty and Growth Conditions in Private Optimization
We develop algorithms for private stochastic convex optimization that adapt to the hardness of the specific function we wish to optimize.
Federated Asymptotics: a model to compare federated learning algorithms
We propose an asymptotic framework to analyze the performance of (personalized) federated learning algorithms.
Predictive Inference with Weak Supervision
The expense of acquiring labels in large-scale statistical machine learning makes partially and weakly-labeled data attractive, though it is not always apparent how to leverage such data for model fitting or validation.
Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression
We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data.
Query-Adaptive Predictive Inference with Partial Labels
The cost and scarcity of fully supervised labels in statistical machine learning encourage using partially labeled data for model validation as a cheaper and more accessible alternative.
How many labelers do you have? A closer look at gold-standard labels
The construction of most supervised learning datasets revolves around collecting multiple labels for each instance, then aggregating the labels to form a type of ``gold-standard.''.
Subspace Recovery from Heterogeneous Data with Non-isotropic Noise
Our goal is to recover the linear subspace shared by $\mu_1,\ldots,\mu_n$ using the data points from all users, where every data point from user $i$ is formed by adding an independent mean-zero noise vector to $\mu_i$.
Private optimization in the interpolation regime: faster rates and hardness results
In non-private stochastic convex optimization, stochastic gradient methods converge much faster on interpolation problems -- problems where there exists a solution that simultaneously minimizes all of the sample losses -- than on non-interpolating ones; we show that generally similar improvements are impossible in the private setting.
A Fast Algorithm for Adaptive Private Mean Estimation
We design an $(\varepsilon, \delta)$-differentially private algorithm to estimate the mean of a $d$-variate distribution, with unknown covariance $\Sigma$, that is adaptive to $\Sigma$.
Differentially Private Heavy Hitter Detection using Federated Analytics
In this work, we study practical heuristics to improve the performance of prefix-tree based algorithms for differentially private heavy hitter detection.
Resampling methods for Private Statistical Inference
We consider the task of constructing confidence intervals with differential privacy.
