Search Results for author:
Found 41 papers, 5 papers with code
Offline Multi-task Transfer RL with Representational Penalization
We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in finding a good policy for a target task.
Learning Optimal Tax Design in Nonatomic Congestion Games
We study how to learn the optimal tax design to maximize the efficiency in nonatomic congestion games.
Initializing Services in Interactive ML Systems for Diverse Users
(ii) Suboptimal Local Solutions: The total loss (sum of loss functions across all users and all services) landscape is not convex even if the individual losses on a single service are convex, making it likely for the learning dynamics to get stuck in local minima.
A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
For robust identification, it is well-known that if arms are chosen randomly and non-adaptively from a G-optimal design over $\mathcal{X}$ at each time then the error probability decreases as $\exp(-T\Delta^2_{(1)}/d)$, where $\Delta_{(1)} = \min_{x \neq x^*} (x^* - x)^\top \frac{1}{T}\sum_{t=1}^T \theta_t$.
A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
Specifically, we focus on games with bandit feedback, where testing an equilibrium can result in substantial regret even when the gap to be tested is small, and the existence of multiple optimal solutions (equilibria) in stationary games poses extra challenges.
Stochastic Contextual Bandits with Long Horizon Rewards
The growing interest in complex decision-making and language modeling problems highlights the importance of sample-efficient learning over very long horizons.
Offline congestion games: How feedback type affects data coverage requirement
Starting from the facility-level (a. k. a., semi-bandit) feedback, we propose a novel one-unit deviation coverage condition and give a pessimism-type algorithm that can recover an approximate NE.
Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies
Gradient-based methods have been widely used for system design and optimization in diverse application domains.
Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates
We present the implementation of nonlinear control algorithms based on linear and quadratic approximations of the objective from a functional viewpoint.
Online SuBmodular + SuPermodular (BP) Maximization with Bandit Feedback
At round $i$, a user with unknown utility $h_q$ arrives; the optimizer selects a new item to add to $S_q$, and receives a noisy marginal gain.
Emergent segmentation from participation dynamics and multi-learner retraining
We study the participation and retraining dynamics that arise when both the learners and sub-populations of users are \emph{risk-reducing}, which cover a broad class of updates including gradient descent, multiplicative weights, etc.
Learning in Congestion Games with Bandit Feedback
We propose a centralized algorithm for Markov congestion games, whose sample complexity again has only polynomial dependence on all relevant problem parameters, but not the size of the action set.
Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments
This paper studies the problem of expected loss minimization given a data distribution that is dependent on the decision-maker's action and evolves dynamically in time according to a geometric decay process.
System Identification via Nuclear Norm Regularization
Hankel regularization encourages the low-rankness of the Hankel matrix, which maps to the low-orderness of the system.
Flat minima generalize for low-rank matrix recovery
Empirical evidence suggests that for a variety of overparameterized nonlinear models, most notably in neural network training, the growth of the loss around a minimizer strongly impacts its performance.
Towards Sample-efficient Overparameterized Meta-learning
Specifically, for (1), we first show that learning the optimal representation coincides with the problem of designing a task-aware regularization to promote inductive bias.
Multiplayer Performative Prediction: Learning in Decision-Dependent Games
We show that under mild assumptions, the performatively stable equilibria can be found efficiently by a variety of algorithms, including repeated retraining and the repeated (stochastic) gradient method.
Fast First-Order Methods for Monotone Strongly DR-Submodular Maximization
Then, we study $L$-smooth monotone strongly DR-submodular functions that have bounded curvature, and we show how to exploit such additional structure to obtain algorithms with improved approximation guarantees and faster convergence rates for the maximization problem.
Selective Sampling for Online Best-arm Identification
The main results of this work precisely characterize this trade-off between labeled samples and stopping time and provide an algorithm that nearly-optimally achieves the minimal label complexity given a desired stopping time.
Improved Regret Bounds for Online Submodular Maximization
For $(1)$, we obtain the first logarithmic regret bounds.
Near-Optimal Randomized Exploration for Tabular Markov Decision Processes
To achieve the desired result, we develop 1) a new clipping operation to ensure both the probability of being optimistic and the probability of being pessimistic are lower bounded by a constant, and 2) a new recursive formula for the absolute value of estimation errors to analyze the regret.
Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning
We prove that subspace-based representations can be learned in a sample-efficient manner and provably benefit future tasks in terms of sample complexity.
Function Design for Improved Competitive Ratio in Online Resource Allocation with Procurement Costs
We study the problem of online resource allocation, where multiple customers arrive sequentially and the seller must irrevocably allocate resources to each incoming customer while also facing a procurement cost for the total allocation.
A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints
In this paper, we consider an online optimization problem in which the reward functions are DR-submodular, and in addition to maximizing the total reward, the sequence of decisions must satisfy some convex constraints on average.
Finite Sample System Identification: Improved Rates and the Role of Regularization
This paper studies low-order linear system identification via regularized regression.
Online DR-Submodular Maximization with Stochastic Cumulative Constraints
Stochastic long-term constraints arise naturally in applications where there is a limited budget or resource available and resource consumption at each step is governed by stochastically time-varying environments.
Competitive Algorithms for Online Budget-Constrained Continuous DR-Submodular Problems
In this paper, we study a certain class of online optimization problems, where the goal is to maximize a function that is not necessarily concave and satisfies the Diminishing Returns (DR) property under budget constraints.
Online Continuous DR-Submodular Maximization with Long-Term Budget Constraints
In this paper, we study a class of online optimization problems with long-term budget constraints where the objective functions are not necessarily concave (nor convex) but they instead satisfy the Diminishing Returns (DR) property.
Escaping from saddle points on Riemannian manifolds
We consider minimizing a nonconvex, smooth function $f$ on a Riemannian manifold $\mathcal{M}$.
New Computational and Statistical Aspects of Regularized Regression with Application to Rare Feature Selection and Aggregation
Prior knowledge on properties of a target model often come as discrete or combinatorial descriptions.
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an "end-to-end" approach, directly optimizing the performance metric of interest 3) they inherently allow for richly parameterized policies.
Global Convergence of Policy Gradient Methods for Linearized Control Problems
Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model; 2) they are an "end-to-end" approach, directly optimizing the performance metric of interest; 3) they inherently allow for richly parameterized policies.
Designing smoothing functions for improved worst-case competitive ratio in online optimization
Online optimization covers problems such as online resource allocation, online bipartite matching, adwords (a central problem in e-commerce and advertising), and adwords with separable concave returns.
Exploiting Tradeoffs for Exact Recovery in Heterogeneous Stochastic Block Models
The Stochastic Block Model (SBM) is a widely used random graph model for networks with communities.
Relative Density and Exact Recovery in Heterogeneous Stochastic Block Models
For instance, $\log n$ is considered to be the standard lower bound on the cluster size for exact recovery via convex methods, for homogenous SBM.
Variational Gram Functions: Convex Analysis and Optimization
We propose a new class of convex penalty functions, called \emph{variational Gram functions} (VGFs), that can promote pairwise relations, such as orthogonality, among a set of vectors in a vector space.
Exponentiated Subgradient Algorithm for Online Optimization under the Random Permutation Model
Online optimization problems arise in many resource allocation tasks, where the future demands for each resource and the associated utility functions change over time and are not known apriori, yet resources need to be allocated at every point in time despite the future uncertainty.
Universal Convexification via Risk-Aversion
We develop a framework for convexifying a fairly general class of optimization problems.
Learning Graphical Models With Hubs
We consider the problem of learning a high-dimensional graphical model in which certain hub nodes are highly-connected to many other nodes.
Node-Based Learning of Multiple Gaussian Graphical Models
We consider estimation under two distinct assumptions: (1) differences between the K networks are due to individual nodes that are perturbed across conditions, or (2) similarities among the K networks are due to the presence of common hub nodes that are shared across all K networks.
Structured Learning of Gaussian Graphical Models
We consider estimation of multiple high-dimensional Gaussian graphical models corresponding to a single set of nodes under several distinct conditions.
