Search Results for author: Michael I. Jordan

Found 104 papers, 19 papers with code

A Unifying Perspective on Multi-Calibration: Unleashing Game Dynamics for Multi-Objective Learning

no code implementations21 Feb 2023 Nika Haghtalab, Michael I. Jordan, Eric Zhao

We provide a unifying framework for the design and analysis of multi-calibrated and moment-multi-calibrated predictors.


Deterministic Nonsmooth Nonconvex Optimization

no code implementations16 Feb 2023 Michael I. Jordan, Guy Kornowski, Tianyi Lin, Ohad Shamir, Manolis Zampetakis

In particular, we prove a lower bound of $\Omega(d)$ for any deterministic algorithm.

Accelerated First-Order Optimization under Nonlinear Constraints

no code implementations1 Feb 2023 Michael Muehlebach, Michael I. Jordan

We exploit analogies between first-order algorithms for constrained optimization and non-smooth dynamical systems to design a new class of accelerated first-order algorithms for constrained optimization.

Online Learning in Stackelberg Games with an Omniscient Follower

no code implementations27 Jan 2023 Geng Zhao, Banghua Zhu, Jiantao Jiao, Michael I. Jordan

We analyze the sample complexity of regret minimization in this repeated Stackelberg game.

Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons

no code implementations26 Jan 2023 Banghua Zhu, Jiantao Jiao, Michael I. Jordan

Our analysis shows that when the true reward function is linear, the widely used maximum likelihood estimator (MLE) converges under both the Bradley-Terry-Luce (BTL) model and the Plackett-Luce (PL) model.

reinforcement-learning Reinforcement Learning (RL)

Prediction-Powered Inference

1 code implementation23 Jan 2023 Anastasios N. Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I. Jordan, Tijana Zrnic

We introduce prediction-powered inference $\unicode{x2013}$ a framework for performing valid statistical inference when an experimental data set is supplemented with predictions from a machine-learning system.


Incentive-Aware Recommender Systems in Two-Sided Markets

no code implementations23 Nov 2022 Xiaowu Dai, YUAN, QI, Michael I. Jordan

Online platforms in the Internet Economy commonly incorporate recommender systems that recommend arms (e. g., products) to agents (e. g., users).

Fairness Recommendation Systems

The Sample Complexity of Online Contract Design

no code implementations10 Nov 2022 Banghua Zhu, Stephen Bates, Zhuoran Yang, Yixin Wang, Jiantao Jiao, Michael I. Jordan

This result shows that exponential-in-$m$ samples are sufficient and necessary to learn a near-optimal contract, resolving an open problem on the hardness of online contract design.

Nesterov Meets Optimism: Rate-Optimal Optimistic-Gradient-Based Method for Stochastic Bilinearly-Coupled Minimax Optimization

no code implementations31 Oct 2022 Chris Junchi Li, Angela Yuan, Gauthier Gidel, Michael I. Jordan

We provide a novel first-order optimization algorithm for bilinearly-coupled strongly-convex-concave minimax optimization called the AcceleratedGradient OptimisticGradient (AG-OG).

A Primal-dual Approach for Solving Variational Inequalities with General-form Constraints

1 code implementation27 Oct 2022 Tatjana Chavdarova, Matteo Pagliardini, Tong Yang, Michael I. Jordan

We prove its convergence and show that the gap function of the last iterate of this inexact-ACVI method decreases at a rate of $\mathcal{O}(\frac{1}{\sqrt{K}})$ when the operator is $L$-Lipschitz and monotone, provided that the errors decrease at appropriate rates.

Explicit Second-Order Min-Max Optimization Methods with Optimal Convergence Guarantee

no code implementations23 Oct 2022 Tianyi Lin, Panayotis Mertikopoulos, Michael I. Jordan

We propose and analyze exact and inexact regularized Newton-type methods for finding a global saddle point of a \textit{convex-concave} unconstrained min-max optimization problem.

Second-order methods

On-Demand Sampling: Learning Optimally from Multiple Distributions

1 code implementation22 Oct 2022 Nika Haghtalab, Michael I. Jordan, Eric Zhao

Social and real-world considerations such as robustness, fairness, social welfare and multi-agent tradeoffs have given rise to multi-distribution learning paradigms, such as collaborative, group distributionally robust, and fair federated learning.

Fairness Federated Learning +1

A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design

no code implementations19 Oct 2022 Rui Ai, Boxiang Lyu, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan

First, from the seller's perspective, we need to efficiently explore the environment in the presence of potentially nontruthful bidders who aim to manipulates seller's policy.

reinforcement-learning Reinforcement Learning (RL)

QuTE: decentralized multiple testing on sensor networks with false discovery rate control

no code implementations9 Oct 2022 Aaditya Ramdas, Jianbo Chen, Martin J. Wainwright, Michael I. Jordan

We consider the setting where distinct agents reside on the nodes of an undirected graph, and each agent possesses p-values corresponding to one or more hypotheses local to its node.

A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning

no code implementations30 Sep 2022 Zixiang Chen, Chris Junchi Li, Angela Yuan, Quanquan Gu, Michael I. Jordan

With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL).

reinforcement-learning Reinforcement Learning (RL)

Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization

no code implementations12 Sep 2022 Tianyi Lin, Zeyu Zheng, Michael I. Jordan

Nonsmooth nonconvex optimization problems broadly emerge in machine learning and business decision making, whereas two core challenges impede the development of efficient solution methods with finite-time convergence guarantee: the lack of computationally tractable optimality criterion and the lack of computationally powerful oracles.

Decision Making

Competition, Alignment, and Equilibria in Digital Marketplaces

no code implementations30 Aug 2022 Meena Jagadeesan, Michael I. Jordan, Nika Haghtalab

Nonetheless, the data sharing assumptions impact what mechanism drives misalignment and also affect the specific form of misalignment (e. g. the quality of the best-case and worst-case market outcomes).

Empirical Gateaux Derivatives for Causal Inference

no code implementations29 Aug 2022 Michael I. Jordan, Yixin Wang, Angela Zhou

We then derive requirements on the rates of numerical approximation in perturbation and smoothing that preserve the statistical benefits of one-step adjustments, such as rate-double-robustness.

Causal Inference

Valid Inference after Causal Discovery

no code implementations11 Aug 2022 Paula Gradu, Tijana Zrnic, Yixin Wang, Michael I. Jordan

Causal discovery and causal effect estimation are two fundamental tasks in causal inference.

Causal Discovery Causal Inference

Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium

no code implementations10 Aug 2022 Chris Junchi Li, Dongruo Zhou, Quanquan Gu, Michael I. Jordan

We consider learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation, where the action-value function is approximated by a function in a Reproducing Kernel Hilbert Space (RKHS).

Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata

no code implementations14 Jul 2022 Tatjana Chavdarova, Ya-Ping Hsieh, Michael I. Jordan

Algorithms that solve zero-sum games, multi-objective agent objectives, or, more generally, variational inequality (VI) problems are notoriously unstable on general problems.

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

1 code implementation13 Jul 2022 Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan

Leveraging this observation, we propose a Train-Convexify-Train (TCT) procedure to sidestep this issue: first, learn features using off-the-shelf methods (e. g., FedAvg); then, optimize a convexified problem obtained from the network's empirical neural tangent kernel approximation.

Federated Learning

Mechanisms that Incentivize Data Sharing in Federated Learning

no code implementations10 Jul 2022 Sai Praneeth Karimireddy, Wenshuo Guo, Michael I. Jordan

Federated learning is typically considered a beneficial technology which allows multiple agents to collaborate with each other, improve the accuracy of their models, and solve problems which are otherwise too data-intensive / expensive to be solved individually.

Federated Learning

Recommendation Systems with Distribution-Free Reliability Guarantees

no code implementations4 Jul 2022 Anastasios N. Angelopoulos, Karl Krauth, Stephen Bates, Yixin Wang, Michael I. Jordan

Building from a pre-trained ranking model, we show how to return a set of items that is rigorously guaranteed to contain mostly good items.

Learning-To-Rank Recommendation Systems

Breaking Feedback Loops in Recommender Systems with Causal Inference

no code implementations4 Jul 2022 Karl Krauth, Yixin Wang, Michael I. Jordan

Our main observation is that a recommender system does not suffer from feedback loops if it reasons about causal quantities, namely the intervention distributions of recommendations on user ratings.

Causal Inference Recommendation Systems

NumS: Scalable Array Programming for the Cloud

no code implementations28 Jun 2022 Melih Elibol, Vinamra Benara, Samyu Yagati, Lianmin Zheng, Alvin Cheung, Michael I. Jordan, Ion Stoica

LSHS is a local search method which optimizes operator placement by minimizing maximum memory and network load on any given node within a distributed system.

regression Scheduling

Modeling Content Creator Incentives on Algorithm-Curated Platforms

no code implementations27 Jun 2022 Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus, Sarah Dean

We prove that seemingly innocuous algorithmic choices -- e. g., non-negative vs. unconstrained factorization -- significantly affect the existence and character of (Nash) equilibria in exposure games.

Solving Constrained Variational Inequalities via a First-order Interior Point-based Method

1 code implementation21 Jun 2022 Tong Yang, Michael I. Jordan, Tatjana Chavdarova

We provide convergence guarantees for ACVI in two general classes of problems: (i) when the operator is $\xi$-monotone, and (ii) when it is monotone, some constraints are active and the game is not purely rotational.

Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization

no code implementations17 Jun 2022 Simon S. Du, Gauthier Gidel, Michael I. Jordan, Chris Junchi Li

We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $\min_{\mathbf{x}}\max_{\mathbf{y}}~F(\mathbf{x}) + H(\mathbf{x},\mathbf{y}) - G(\mathbf{y})$, where one has access to stochastic first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$.

Robust Calibration with Multi-domain Temperature Scaling

no code implementations6 Jun 2022 Yaodong Yu, Stephen Bates, Yi Ma, Michael I. Jordan

Uncertainty quantification is essential for the reliable deployment of machine learning models to high-stakes application domains.

First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces

no code implementations4 Jun 2022 Michael I. Jordan, Tianyi Lin, Emmanouil-Vasileios Vlatakis-Gkaragkounis

From optimal transport to robust dimensionality reduction, a plethora of machine learning applications can be cast into the min-max optimization problems over Riemannian manifolds.

Dimensionality Reduction

Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees

1 code implementation24 May 2022 Banghua Zhu, Lun Wang, Qi Pang, Shuai Wang, Jiantao Jiao, Dawn Song, Michael I. Jordan

In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for strongly convex losses.

Federated Learning

Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback

no code implementations15 May 2022 Tianyi Lin, Aldo Pacchiano, Yaodong Yu, Michael I. Jordan

Motivated by applications to online learning in sparse estimation and Bayesian optimization, we consider the problem of online unconstrained nonsubmodular minimization with delayed costs in both full information and bandit feedback settings.

Principal-Agent Hypothesis Testing

no code implementations13 May 2022 Stephen Bates, Michael I. Jordan, Michael Sklar, Jake A. Soloff

The pharmaceutical company wishes to sell a product to make a profit, and the FDA wishes to ensure that only efficacious drugs are released to the public.

First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems

no code implementations7 Apr 2022 Michael I. Jordan, Tianyi Lin, Manolis Zampetakis

We consider the problem of computing an equilibrium in a class of \textit{nonlinear generalized Nash equilibrium problems (NGNEPs)} in which the strategy sets for each player are defined by equality and inequality constraints that may depend on the choices of rival players.

Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents

no code implementations20 Mar 2022 Alessandro Barp, Lancelot Da Costa, Guilherme França, Karl Friston, Mark Girolami, Michael I. Jordan, Grigorios A. Pavliotis

In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making.

Decision Making

Off-Policy Evaluation with Policy-Dependent Optimization Response

no code implementations25 Feb 2022 Wenshuo Guo, Michael I. Jordan, Angela Zhou

Under this framework, a decision-maker's utility depends on the policy-dependent optimization, which introduces a fundamental challenge of \textit{optimization} bias even for the case of policy evaluation.

Causal Inference Decision Making +1

Partial Identification with Noisy Covariates: A Robust Optimization Approach

no code implementations22 Feb 2022 Wenshuo Guo, Mingzhang Yin, Yixin Wang, Michael I. Jordan

Directly adjusting for these imperfect measurements of the covariates can lead to biased causal estimates.

Causal Inference

Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning

no code implementations22 Feb 2022 Jibang Wu, Zixuan Zhang, Zhe Feng, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan, Haifeng Xu

This paper proposes a novel model of sequential information design, namely the Markov persuasion processes (MPPs), where a sender, with informational advantage, seeks to persuade a stream of myopic receivers to take actions that maximizes the sender's cumulative utilities in a finite horizon Markovian environment with varying prior and utility functions.

reinforcement-learning Reinforcement Learning (RL)

No-Regret Learning in Partially-Informed Auctions

no code implementations22 Feb 2022 Wenshuo Guo, Michael I. Jordan, Ellen Vitercik

We formalize this problem as an online learning task where the goal is to have low regret with respect to a myopic oracle that has perfect knowledge of the distribution over items and the seller's masking function.

Improving Generalization via Uncertainty Driven Perturbations

no code implementations11 Feb 2022 Matteo Pagliardini, Gilberto Manunza, Martin Jaggi, Michael I. Jordan, Tatjana Chavdarova

We show that UDP is guaranteed to achieve the maximum margin decision boundary on linear models and that it notably increases it on challenging simulated datasets.

Transferred Q-learning

no code implementations9 Feb 2022 Elynn Y. Chen, Michael I. Jordan, Sai Li

We consider $Q$-learning with knowledge transfer, using samples from a target reinforcement learning (RL) task as well as source samples from different but related RL tasks.

Offline RL Q-Learning +2

Conformal prediction for the design problem

1 code implementation8 Feb 2022 Clara Fannjiang, Stephen Bates, Anastasios N. Angelopoulos, Jennifer Listgarten, Michael I. Jordan

This is challenging because of a characteristic type of distribution shift between the training and test data in the design setting -- one in which the training and test data are statistically dependent, as the latter is chosen based on the former.

Conformal Prediction

Robust Estimation for Nonparametric Families via Generative Adversarial Networks

no code implementations2 Feb 2022 Banghua Zhu, Jiantao Jiao, Michael I. Jordan

Prior work focus on the problem of robust mean and covariance estimation when the true distribution lies in the family of Gaussian distributions or elliptical distributions, and analyze depth or scoring rule based GAN losses for the problem.

Reinforcement Learning with Heterogeneous Data: Estimation and Inference

no code implementations31 Jan 2022 Elynn Y. Chen, Rui Song, Michael I. Jordan

Reinforcement Learning (RL) has the promise of providing data-driven support for decision-making in a wide range of problems in healthcare, education, business, and other domains.

Decision Making reinforcement-learning +1

Dynamic Thresholding for Online Distributed Data Selection

1 code implementation25 Jan 2022 Mariel A. Werner, Anastasios Angelopoulos, Stephen Bates, Michael I. Jordan

The blessing of ubiquitous data also comes with a curse: the communication, storage, and labeling of massive, mostly redundant datasets.

Active Learning

Optimal variance-reduced stochastic approximation in Banach spaces

no code implementations21 Jan 2022 Wenlong Mou, Koulik Khamaru, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan

We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space.


A Statistical Analysis of Polyak-Ruppert Averaged Q-learning

no code implementations29 Dec 2021 Xiang Li, Wenhao Yang, Jiadong Liang, Zhihua Zhang, Michael I. Jordan

We study Q-learning with Polyak-Ruppert averaging in a discounted Markov decision process in synchronous and tabular settings.


Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems

no code implementations29 Dec 2021 Chris Junchi Li, Michael I. Jordan

Motivated by the problem of online canonical correlation analysis, we propose the \emph{Stochastic Scaled-Gradient Descent} (SSGD) algorithm for minimizing the expectation of a stochastic function over a generic Riemannian manifold.

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

no code implementations NeurIPS 2021 Yufeng Zhang, Siyu Chen, Zhuoran Yang, Michael I. Jordan, Zhaoran Wang

Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates.

Representation Learning

Last-Iterate Convergence of Saddle Point Optimizers via High-Resolution Differential Equations

no code implementations27 Dec 2021 Tatjana Chavdarova, Michael I. Jordan, Manolis Zampetakis

However, the convergence properties of these methods are qualitatively different even on simple bilinear games.

Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?

no code implementations27 Dec 2021 Han Zhong, Zhuoran Yang, Zhaoran Wang, Michael I. Jordan

We develop sample-efficient reinforcement learning (RL) algorithms for solving for an SNE in both online and offline settings.

Reinforcement Learning (RL)

Meta-Analysis of Randomized Experiments with Applications to Heavy-Tailed Response Data

no code implementations14 Dec 2021 Nilesh Tripuraneni, Dhruv Madeka, Dean Foster, Dominique Perrault-Joncas, Michael I. Jordan

The key insight of our procedure is that the noisy (but unbiased) difference-of-means estimate can be used as a ground truth ``label" on a portion of the RCT, to test the performance of an estimator trained on the other portion.

ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning

1 code implementation11 Dec 2021 Xiao-Yang Liu, Zechu Li, Zhuoran Yang, Jiahao Zheng, Zhaoran Wang, Anwar Walid, Jian Guo, Michael I. Jordan

In this paper, we present a scalable and elastic library ElegantRL-podracer for cloud-native deep reinforcement learning, which efficiently supports millions of GPU cores to carry out massively parallel training at multiple levels.

reinforcement-learning Reinforcement Learning (RL) +1

Cluster-and-Conquer: A Framework For Time-Series Forecasting

no code implementations26 Oct 2021 Reese Pathak, Rajat Sen, Nikhil Rao, N. Benjamin Erichson, Michael I. Jordan, Inderjit S. Dhillon

Our framework -- which we refer to as "cluster-and-conquer" -- is highly general, allowing for any time-series forecasting and clustering method to be used in each step.

Time Series Forecasting

Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs

1 code implementation20 Oct 2021 Kaichao You, Yong liu, Ziyang Zhang, Jianmin Wang, Michael I. Jordan, Mingsheng Long

(2) The best ranked PTM can either be fine-tuned and deployed if we have no preference for the model's architecture or the target PTM can be tuned by the top $K$ ranked PTMs via a Bayesian procedure that we propose.

On the Self-Penalization Phenomenon in Feature Selection

no code implementations12 Oct 2021 Michael I. Jordan, Keli Liu, Feng Ruan

We describe an implicit sparsity-inducing mechanism based on minimization over a family of kernels: \begin{equation*} \min_{\beta, f}~\widehat{\mathbb{E}}[L(Y, f(\beta^{1/q} \odot X)] + \lambda_n \|f\|_{\mathcal{H}_q}^2~~\text{subject to}~~\beta \ge 0, \end{equation*} where $L$ is the loss, $\odot$ is coordinate-wise multiplication and $\mathcal{H}_q$ is the reproducing kernel Hilbert space based on the kernel $k_q(x, x') = h(\|x-x'\|_q^q)$, where $\|\cdot\|_q$ is the $\ell_q$ norm.

Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

1 code implementation3 Oct 2021 Anastasios N. Angelopoulos, Stephen Bates, Emmanuel J. Candès, Michael I. Jordan, Lihua Lei

We introduce a framework for calibrating machine learning models so that their predictions satisfy explicit, finite-sample statistical guarantees.

BIG-bench Machine Learning Instance Segmentation +3

SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier

no code implementations1 Oct 2021 Adelson Chua, Michael I. Jordan, Rikky Muller

Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress epileptic seizures.

Electroencephalogram (EEG) Seizure Detection +1

Desiderata for Representation Learning: A Causal Perspective

1 code implementation8 Sep 2021 Yixin Wang, Michael I. Jordan

Representation learning constructs low-dimensional representations to summarize essential features of high-dimensional data.


Learning Equilibria in Matching Markets from Bandit Feedback

no code implementations NeurIPS 2021 Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt

Large-scale, two-sided matching platforms must find market outcomes that align with user preferences while simultaneously learning these preferences from data.

Optimization on manifolds: A symplectic approach

no code implementations23 Jul 2021 Guilherme França, Alessandro Barp, Mark Girolami, Michael I. Jordan

There has been great interest in using tools from dynamical systems and numerical analysis of differential equations to understand and construct new optimization methods.

Data Sharing Markets

no code implementations19 Jul 2021 Mohammad Rasouli, Michael I. Jordan

We model bilateral sharing as a network formation game and show the existence of strongly stable outcome under the top agents property by allowing limited complementarity.

On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems

no code implementations17 Jul 2021 Michael Muehlebach, Michael I. Jordan

We introduce a class of first-order methods for smooth constrained optimization that are based on an analogy to non-smooth dynamical systems.

Robust Learning of Optimal Auctions

no code implementations NeurIPS 2021 Wenshuo Guo, Michael I. Jordan, Manolis Zampetakis

The proposed algorithms operate beyond the setting of bounded distributions that have been studied in prior works, and are guaranteed to obtain a fraction $1-O(\alpha)$ of the optimal revenue under the true distribution when the distributions are MHR.

Evaluating Sensitivity to the Stick-Breaking Prior in Bayesian Nonparametrics

no code implementations8 Jul 2021 Ryan Giordano, Runjing Liu, Michael I. Jordan, Tamara Broderick

Bayesian models based on the Dirichlet process and other stick-breaking priors have been proposed as core ingredients for clustering, topic modeling, and other unsupervised learning tasks.

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

no code implementations30 Jun 2021 Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

We study the stochastic bilinear minimax optimization problem, presenting an analysis of the same-sample Stochastic ExtraGradient (SEG) method with constant step size, and presenting variations of the method that yield favorable convergence.

Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence

no code implementations30 Jun 2021 Ghassen Jerfel, Serena Wang, Clara Fannjiang, Katherine A. Heller, Yian Ma, Michael I. Jordan

We thus propose a novel combination of optimization and sampling techniques for approximate Bayesian inference by constructing an IS proposal distribution through the minimization of a forward KL (FKL) divergence.

Bayesian Inference Variational Inference

On component interactions in two-stage recommender systems

no code implementations28 Jun 2021 Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus

Thanks to their scalability, two-stage recommenders are used by many of today's largest online platforms, including YouTube, LinkedIn, and Pinterest.

Recommendation Systems

Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning

no code implementations28 Jun 2021 Koulik Khamaru, Eric Xia, Martin J. Wainwright, Michael I. Jordan

Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure.


The Stereotyping Problem in Collaboratively Filtered Recommender Systems

no code implementations23 Jun 2021 Wenshuo Guo, Karl Krauth, Michael I. Jordan, Nikhil Garg

First, we introduce a notion of joint accessibility, which measures the extent to which a set of items can jointly be accessed by users.

Collaborative Filtering Recommendation Systems

Who Leads and Who Follows in Strategic Classification?

no code implementations NeurIPS 2021 Tijana Zrnic, Eric Mazumdar, S. Shankar Sastry, Michael I. Jordan

In particular, by generalizing the standard model to allow both players to learn over time, we show that a decision-maker that makes updates faster than the agents can reverse the order of play, meaning that the agents lead and the decision-maker follows.


Test-time Collective Prediction

no code implementations NeurIPS 2021 Celestine Mendler-Dünner, Wenshuo Guo, Stephen Bates, Michael I. Jordan

An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points.

PAC Best Arm Identification Under a Deadline

no code implementations6 Jun 2021 Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica, Michael I. Jordan, Ken Goldberg, Joseph E. Gonzalez

In this work, the decision-maker is given a deadline of $T$ rounds, where, on each round, it can adaptively choose which arms to pull and how many times to pull them; this distinguishes the number of decisions made (i. e., time or number of rounds) from the number of samples acquired (cost).

Parallelizing Contextual Bandits

no code implementations21 May 2021 Jeffrey Chan, Aldo Pacchiano, Nilesh Tripuraneni, Yun S. Song, Peter Bartlett, Michael I. Jordan

Standard approaches to decision-making under uncertainty focus on sequential exploration of the space of decisions.

Decision Making Decision Making Under Uncertainty +1

Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization

no code implementations27 Apr 2021 Yaodong Yu, Tianyi Lin, Eric Mazumdar, Michael I. Jordan

Distributionally robust supervised learning (DRSL) is emerging as a key paradigm for building reliable machine learning systems for real-world applications -- reflecting the need for classifiers and predictive models that are robust to the distribution shifts that arise from phenomena such as selection bias or nonstationarity.

BIG-bench Machine Learning Selection bias

Multi-Source Causal Inference Using Control Variates

no code implementations30 Mar 2021 Wenshuo Guo, Serena Wang, Peng Ding, Yixin Wang, Michael I. Jordan

Across simulations and two case studies with real data, we show that this control variate can significantly reduce the variance of the ATE estimate.

Causal Inference Epidemiology +2

On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective

no code implementations27 Mar 2021 Tyler Westenbroek, Max Simchowitz, Michael I. Jordan, S. Shankar Sastry

The widespread adoption of nonlinear Receding Horizon Control (RHC) strategies by industry has led to more than 30 years of intense research efforts to provide stability guarantees for these methods.

A Variational Inequality Approach to Bayesian Regression Games

no code implementations24 Mar 2021 Wenshuo Guo, Michael I. Jordan, Tianyi Lin

Bayesian regression games are a special class of two-player general-sum Bayesian games in which the learner is partially informed about the adversary's objective through a Bayesian prior.

regression Stochastic Optimization

Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data

1 code implementation5 Mar 2021 Esther Rolf, Theodora Worledge, Benjamin Recht, Michael I. Jordan

Collecting more diverse and representative training data is often touted as a remedy for the disparate performance of machine learning predictors across subpopulations.

Private Prediction Sets

1 code implementation11 Feb 2021 Anastasios N. Angelopoulos, Stephen Bates, Tijana Zrnic, Michael I. Jordan

Our method follows the general approach of split conformal prediction; we use holdout data to calibrate the size of the prediction sets but preserve privacy by using a privatized quantile subroutine.

Conformal Prediction Decision Making

Distribution-Free, Risk-Controlling Prediction Sets

2 code implementations7 Jan 2021 Stephen Bates, Anastasios Angelopoulos, Lihua Lei, Jitendra Malik, Michael I. Jordan

While improving prediction accuracy has been the focus of machine learning in recent years, this alone does not suffice for reliable decision-making.

BIG-bench Machine Learning Classification +8

Stochastic Approximation for Online Tensorial Independent Component Analysis

no code implementations28 Dec 2020 Chris Junchi Li, Michael I. Jordan

For estimating one component, we provide a dynamics-based analysis to prove that our online tensorial ICA algorithm with a specific choice of stepsize achieves a sharp finite-sample error bound.

Dimensionality Reduction

Bandit Learning in Decentralized Matching Markets

no code implementations14 Dec 2020 Lydia T. Liu, Feng Ruan, Horia Mania, Michael I. Jordan

We study two-sided matching markets in which one side of the market (the players) does not have a priori knowledge about its preferences for the other side (the arms) and is required to learn its preferences from experience.

Optimal Mean Estimation without a Variance

no code implementations24 Nov 2020 Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, Michael I. Jordan

Concretely, given a sample $\mathbf{X} = \{X_i\}_{i = 1}^n$ from a distribution $\mathcal{D}$ over $\mathbb{R}^d$ with mean $\mu$ which satisfies the following \emph{weak-moment} assumption for some ${\alpha \in [0, 1]}$: \begin{equation*} \forall \|v\| = 1: \mathbb{E}_{X \thicksim \mathcal{D}}[\lvert \langle X - \mu, v\rangle \rvert^{1 + \alpha}] \leq 1, \end{equation*} and given a target failure probability, $\delta$, our goal is to design an estimator which attains the smallest possible confidence interval as a function of $n, d,\delta$.

On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces

no code implementations9 Nov 2020 Zhuoran Yang, Chi Jin, Zhaoran Wang, Mengdi Wang, Michael I. Jordan

The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions.

Reinforcement Learning (RL)

Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization

no code implementations31 Oct 2020 Jelena Diakonikolas, Constantinos Daskalakis, Michael I. Jordan

The use of min-max optimization in adversarial training of deep neural network classifiers and training of generative adversarial networks has motivated the study of nonconvex-nonconcave optimization objectives, which frequently arise in these applications.

Learning Strategies in Decentralized Matching Markets under Uncertain Preferences

no code implementations29 Oct 2020 Xiaowu Dai, Michael I. Jordan

We study the problem of decision-making in the setting of a scarcity of shared resources when the preferences of agents are unknown a priori and must be learned from data.

Decision Making Fairness

Behavior-Guided Reinforcement Learning

no code implementations25 Sep 2019 Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Anna Choromanska, Krzysztof Choromanski, Michael I. Jordan

We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space.

reinforcement-learning Reinforcement Learning (RL)

Posterior Distribution for the Number of Clusters in Dirichlet Process Mixture Models

no code implementations23 May 2019 Chiao-Yu Yang, Eric Xia, Nhat Ho, Michael I. Jordan

In this work, we provide a rigorous study for the posterior distribution of the number of clusters in DPMM under different prior distributions on the parameters and constraints on the distributions of the data.

Bayesian Nonparametric Inference of Switching Linear Dynamical Systems

1 code implementation19 Mar 2010 Emily B. Fox, Erik B. Sudderth, Michael I. Jordan, Alan S. Willsky

Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes.

Latent Dirichlet Allocation

2 code implementations1 Jan 2003 David M. Blei, Andrew Y. Ng, Michael I. Jordan

Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities.

Collaborative Filtering Text Categorization +2

Cannot find the paper you are looking for? You can Submit a new open access paper.