Search Results for author:
Found 37 papers, 3 papers with code
Extragradient Type Methods for Riemannian Variational Inequality Problems
In the context of Euclidean space, it is established that the last-iterates of both the extragradient (EG) and past extragradient (PEG) methods converge to the solution of monotone variational inequality problems at a rate of $O\left(\frac{1}{\sqrt{T}}\right)$ (Cai et al., 2022).
On the Robustness of Epoch-Greedy in Multi-Agent Contextual Bandit Mechanisms
Efficient learning in multi-armed bandit mechanisms such as pay-per-click (PPC) auctions typically involves three challenges: 1) inducing truthful bidding behavior (incentives), 2) using personalization in the users (context), and 3) circumventing manipulations in click patterns (corruptions).
Randomized Quantization is All You Need for Differential Privacy in Federated Learning
To the best of our knowledge, this is the first study that solely relies on randomized quantization without incorporating explicit discrete noise to achieve Renyi DP guarantees in Federated Learning systems.
On Riemannian Projection-free Online Learning
The projection operation is a critical component in a wide range of optimization algorithms, such as online gradient descent (OGD), for enforcing constraints and achieving optimal regret bounds.
Faster Margin Maximization Rates for Generic Optimization Methods
In contrast, generic optimization methods, such as mirror descent and steepest descent, have been shown to converge to maximal margin classifiers defined by alternative geometries.
A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks
We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization.
Minimizing Dynamic Regret on Geodesic Metric Spaces
In this paper, we consider the sequential decision problem where the goal is to minimize the general dynamic regret on a complete Riemannian manifold.
On Accelerated Perceptrons and Beyond
The classical Perceptron algorithm of Rosenblatt can be used to find a linear threshold function to correctly classify $n$ linearly separable data points, assuming the classes are separated by some margin $\gamma > 0$.
Adaptive Oracle-Efficient Online Learning
The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale.
No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization
We develop an algorithmic framework for solving convex optimization problems using no-regret game dynamics.
Escaping Saddle Points Faster with Stochastic Momentum
At the same time, a widely-observed empirical phenomenon is that in training deep networks stochastic momentum appears to significantly improve convergence time, variants of it have flourished in the development of other popular update methods, e. g. ADAM [KB15], AMSGrad [RKK18], etc.
A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness
This apparent lack of robustness has led researchers to propose methods that can help to prevent an adversary from having such capabilities.
Linear Separation via Optimism
Binary linear classification has been explored since the very early days of the machine learning literature.
Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron
Over-parametrization has become a popular technique in deep learning.
A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network
Our result shows that with the appropriate choice of parameters Polyak's momentum has a rate of $(1-\Theta(\frac{1}{\sqrt{\kappa'}}))^t$.
Quickly Finding a Benign Region via Heavy Ball Momentum in Non-Convex Optimization
The Heavy Ball Method, proposed by Polyak over five decades ago, is a first-order method for optimizing continuous functions.
Online Kernel based Generative Adversarial Networks
We propose a novel approach that resolves many of these issues by relying on a kernel-based non-parametric discriminator that is highly amenable to online training---we call this the Online Kernel-based Generative Adversarial Networks (OKGAN).
Active Sampling for Min-Max Fairness
We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization.
Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs
Finding the Nash Equilibrium (NE) of a two player zero-sum game is core to many problems in statistics, optimization, and economics, and for a fixed game matrix this can be easily reduced to solving a linear program.
Last-iterate convergence rates for min-max optimization
While classic work in convex-concave min-max optimization relies on average-iterate convergence results, the emergence of nonconvex applications such as training Generative Adversarial Networks has led to renewed interest in last-iterate convergence guarantees.
Acceleration through Optimistic No-Regret Dynamics
In this paper we show that the technique can be enhanced to a rate of $O(1/T^2)$ by extending recent work \cite{RS13, SALS15} that leverages \textit{optimistic learning} to speed up equilibrium computation.
ActiveRemediation: The Search for Lead Pipes in Flint, Michigan
We detail our ongoing work in Flint, Michigan to detect pipes made of lead and other hazardous metals.
Faster Rates for Convex-Concave Games
We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games.
Online Learning via the Differential Privacy Lens
In this paper, we use differential privacy as a lens to examine online learning in both full and partial information settings.
A Data Science Approach to Understanding Residential Water Contamination in Flint
This is the nation's largest dataset on lead in a municipal water system.
On Convergence and Stability of GANs
We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions.
Data Science in Service of Performing Arts: Applying Machine Learning to Predicting Audience Preferences
Performing arts organizations aim to enrich their communities through the arts.
Flint Water Crisis: Data-Driven Risk Assessment Via Residential Water Testing
In this analysis, we find that lead service lines are not the only factor that is predictive of the risk of lead contamination of water.
Fighting Bandits with a New Kind of Smoothness
We define a novel family of algorithms for the adversarial multi-armed bandit problem, and provide a simple analysis technique based on convex smoothing.
Spectral Smoothing via Random Matrix Perturbations
Smoothing the maximum eigenvalue function is important for applications in semidefinite optimization and online learning.
Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier
We show that simulated annealing, a well-studied random walk algorithms, is directly equivalent, in a certain sense, to the central path interior point algorithm for the the entropic universal barrier function.
Low-Cost Learning via Active Data Procurement
Our results in a sense parallel classic sample complexity guarantees, but with the key resource being money rather than quantity of data: With a budget constraint $B$, we give robust risk (predictive error) bounds on the order of $1/\sqrt{B}$.
Online Linear Optimization via Smoothing
We present a new optimization-theoretic approach to analyzing Follow-the-Leader style algorithms, particularly in the setting where perturbations are used as a tool for regularization.
Information Aggregation in Exponential Family Markets
We consider the design of prediction market mechanisms known as automated market makers.
How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal
We consider a popular problem in finance, option pricing, through the lens of an online learning game between Nature and an Investor.
Adaptive Market Making via Online Learning
We consider the design of strategies for \emph{market making} in a market like a stock, commodity, or currency exchange.
Minimax Optimal Algorithms for Unconstrained Linear Optimization
We design and analyze minimax-optimal algorithms for online linear optimization games where the player's choice is unconstrained.
