no code implementations • 29 Apr 2024 • Ezinne Nwankwo, Michael I. Jordan, Angela Zhou
However, if causal effects are heterogeneous and predictable from covariates, personalized treatment decisions can improve individual outcomes and contribute to both efficiency and equity.
no code implementations • 24 Apr 2024 • Tianyu Guo, Sai Praneeth Karimireddy, Michael I. Jordan
Instead of adjusting the distribution shift separately, we use weighted propensity score models to collaboratively adjust for the distribution shift.
no code implementations • 28 Mar 2024 • Drew T. Nguyen, Reese Pathak, Anastasios N. Angelopoulos, Stephen Bates, Michael I. Jordan
Decision-making pipelines are generally characterized by tradeoffs among various risk functions.
1 code implementation • 9 Mar 2024 • Pierre Boyeau, Anastasios N. Angelopoulos, Nir Yosef, Jitendra Malik, Michael I. Jordan
The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming.
no code implementations • 6 Mar 2024 • Antoine Scheid, Daniil Tiapkin, Etienne Boursier, Aymeric Capitaine, El Mahdi El Mhamdi, Eric Moulines, Michael I. Jordan, Alain Durmus
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent.
no code implementations • 15 Feb 2024 • Alireza Fallah, Michael I. Jordan, Ali Makhdoumi, Azarakhsh Malekian
We study a three-layer data market comprising users (data owners), platforms, and a data buyer.
no code implementations • 13 Feb 2024 • Alireza Fallah, Michael I. Jordan, Ali Makhdoumi, Azarakhsh Malekian
We consider a privacy mechanism that provides a degree of protection by probabilistically masking each market segment, and we establish that the resultant set of all consumer-producer utilities forms a convex polygon, characterized explicitly as a linear mapping of a certain high-dimensional convex polytope into $\mathbb{R}^2$.
no code implementations • 29 Jan 2024 • Banghua Zhu, Michael I. Jordan, Jiantao Jiao
Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique that aligns language models closely with human-centric values.
no code implementations • 13 Dec 2023 • Baihe Huang, Hanlin Zhu, Banghua Zhu, Kannan Ramchandran, Michael I. Jordan, Jason D. Lee, Jiantao Jiao
Key to our formulation is a coupling of the output tokens and the rejection region, realized by pseudo-random generators in practice, that allows non-trivial trade-offs between the Type I error and Type II error.
no code implementations • 17 Nov 2023 • Francisca Vasconcelos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos, Georgios Piliouras, Michael I. Jordan
In 2008, Jain and Watrous proposed the first classical algorithm for computing equilibria in quantum zero-sum games using the Matrix Multiplicative Weight Updates (MMWU) method to achieve a convergence rate of $\mathcal{O}(d/\epsilon^2)$ iterations to $\epsilon$-Nash equilibria in the $4^d$-dimensional spectraplex.
no code implementations • 21 Oct 2023 • Tianyi Lin, Marco Cuturi, Michael I. Jordan
Kernel-based optimal transport (OT) estimators offer an alternative, functional estimation procedure to address OT problems from samples.
no code implementations • 21 Oct 2023 • Michael I. Jordan, Tianyi Lin, Zhengyuan Zhou
Online gradient descent (OGD) is well known to be doubly optimal under strong convexity or monotonicity assumptions: (1) in the single-agent setting, it achieves an optimal regret of $\Theta(\log T)$ for strongly convex cost functions; and (2) in the multi-agent setting of strongly monotone games, with each agent employing OGD, we obtain last-iterate convergence of the joint action to a unique Nash equilibrium at an optimal rate of $\Theta(\frac{1}{T})$.
no code implementations • 9 Oct 2023 • Jordan Lekeufack, Anastasios N. Angelopoulos, Andrea Bajcsy, Michael I. Jordan, Jitendra Malik
We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions.
no code implementations • 9 Sep 2023 • Neha S. Wadia, Yatin Dandi, Michael I. Jordan
The rapid progress in machine learning in recent years has been based on a highly productive connection to gradient-based optimization.
no code implementations • 4 Sep 2023 • Nivasini Ananthakrishnan, Stephen Bates, Michael I. Jordan, Nika Haghtalab
To address the lack of a priori knowledge regarding the optimal performance, we give a convex program that can adaptively and efficiently compute the optimal contract.
no code implementations • 25 Jul 2023 • Yaodong Yu, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan
We present Scaff-PD, a fast and communication-efficient algorithm for distributionally robust federated learning.
no code implementations • 7 Jul 2023 • Stephen Bates, Michael I. Jordan, Michael Sklar, Jake A. Soloff
We show how the principal can conduct statistical inference that leverages the information that is revealed by an agent's strategic behavior -- their choice to run a trial or not.
no code implementations • 30 Jun 2023 • Haikuo Yang, Luo Luo, Chris Junchi Li, Michael I. Jordan
We present a method for solving general nonconvex-strongly-convex bilevel optimization problems.
no code implementations • 29 Jun 2023 • Yang Cai, Michael I. Jordan, Tianyi Lin, Argyris Oikonomou, Emmanouil-Vasileios Vlatakis-Gkaragkounis
Numerous applications in machine learning and data analytics can be formulated as equilibrium computation over Riemannian manifolds.
1 code implementation • NeurIPS 2023 • Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
As the scale of machine learning models increases, trends such as scaling laws anticipate consistent downstream improvements in predictive accuracy.
1 code implementation • NeurIPS 2023 • Tiffany Ding, Anastasios N. Angelopoulos, Stephen Bates, Michael I. Jordan, Ryan J. Tibshirani
Standard conformal prediction methods provide a marginal coverage guarantee, which means that for a random test point, the conformal prediction set contains the true label with a user-specified probability.
no code implementations • 13 Jun 2023 • Xinyan Hu, Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt
For content recommender systems such as TikTok and YouTube, the platform's decision algorithm shapes the incentives of content producers, including how much effort the content producers invest in the quality of their content.
no code implementations • 8 Jun 2023 • Baihe Huang, Sai Praneeth Karimireddy, Michael I. Jordan
This creates a tension between the principal (the FL platform designer) who cares about global performance and the agents (the data collectors) who care about local performance.
1 code implementation • 4 Jun 2023 • Banghua Zhu, Hiteshi Sharma, Felipe Vieira Frujeri, Shi Dong, Chenguang Zhu, Michael I. Jordan, Jiantao Jiao
Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences.
1 code implementation • 3 Jun 2023 • Banghua Zhu, Ying Sheng, Lianmin Zheng, Clark Barrett, Michael I. Jordan, Jiantao Jiao
Theoretically, we provide an optimal algorithm for jointly optimizing both approaches to reduce the inference cost in both offline and online tabular settings.
1 code implementation • 27 May 2023 • Charles Lu, Yaodong Yu, Sai Praneeth Karimireddy, Michael I. Jordan, Ramesh Raskar
Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing step to already trained models.
no code implementations • 24 May 2023 • Serena Wang, Stephen Bates, P. M. Aronow, Michael I. Jordan
From the social sciences to machine learning, it has been well documented that metrics to be optimized are not always aligned with social welfare.
no code implementations • 19 May 2023 • Banghua Zhu, Sai Praneeth Karimireddy, Jiantao Jiao, Michael I. Jordan
In this paper, we initiate the study of online learning in the creator economy by modeling the creator economy as a three-party game between the users, platform, and content creators, with the platform interacting with the content creator under a principal-agent model through contracts to encourage better content.
no code implementations • 24 Feb 2023 • Ruitu Xu, Yifei Min, Tianhao Wang, Zhaoran Wang, Michael I. Jordan, Zhuoran Yang
We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market.
no code implementations • 16 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.
no code implementations • 1 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.
no code implementations • 27 Jan 2023 • Geng Zhao, Banghua Zhu, Jiantao Jiao, Michael I. Jordan
We analyze the sample complexity of regret minimization in this repeated Stackelberg game.
no code implementations • 26 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.
2 code implementations • 23 Jan 2023 • Anastasios N. Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I. Jordan, Tijana Zrnic
Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system.
no code implementations • 23 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).
no code implementations • 10 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.
no code implementations • 31 Oct 2022 • Chris Junchi Li, Angela Yuan, Gauthier Gidel, Quanquan Gu, Michael I. Jordan
AG-OG is the first single-call algorithm with optimal convergence rates in both deterministic and stochastic settings for bilinearly coupled minimax optimization problems.
1 code implementation • 27 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.
no code implementations • 23 Oct 2022 • Tianyi Lin, Panayotis Mertikopoulos, Michael I. Jordan
Specifically, we show that the proposed methods generate iterates that remain within a bounded set and that the averaged iterates converge to an $\epsilon$-saddle point within $O(\epsilon^{-2/3})$ iterations in terms of a restricted gap function.
1 code implementation • 22 Oct 2022 • Nika Haghtalab, Michael I. Jordan, Eric Zhao
This improves upon the best known sample complexity bounds for fair federated learning by Mohri et al. and collaborative learning by Nguyen and Zakynthinou by multiplicative factors of $n$ and $\log(n)/\epsilon^3$, respectively.
no code implementations • 19 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.
no code implementations • 9 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.
no code implementations • 30 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).
no code implementations • 12 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.
no code implementations • 30 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).
no code implementations • 29 Aug 2022 • Michael I. Jordan, Yixin Wang, Angela Zhou
We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite differencing, with a focus on functionals that arise in causal inference.
no code implementations • 11 Aug 2022 • Paula Gradu, Tijana Zrnic, Yixin Wang, Michael I. Jordan
Causal discovery and causal effect estimation are two fundamental tasks in causal inference.
no code implementations • 10 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).
no code implementations • 14 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.
1 code implementation • 13 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.
no code implementations • 10 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.
no code implementations • 4 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.
no code implementations • 4 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.
1 code implementation • 28 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.
no code implementations • 27 Jun 2022 • Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus, Sarah Dean
To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
1 code implementation • 21 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.
no code implementations • 17 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 $H$.
no code implementations • 6 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.
no code implementations • 4 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.
2 code implementations • 24 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.
no code implementations • 15 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.
no code implementations • 13 May 2022 • Stephen Bates, Michael I. Jordan, Michael Sklar, Jake A. Soloff
The efficacy of the drug is not known to the regulator, so the pharmaceutical company must run a costly trial to prove efficacy to the regulator.
no code implementations • 7 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.
no code implementations • 20 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.
no code implementations • 7 Mar 2022 • Yifei Min, Tianhao Wang, Ruitu Xu, Zhaoran Wang, Michael I. Jordan, Zhuoran Yang
We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market.
no code implementations • 25 Feb 2022 • Shuang Qiu, Boxiang Lyu, Qinglin Meng, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan
Dynamic mechanism design studies how mechanism designers should allocate resources among agents in a time-varying environment.
no code implementations • 25 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.
no code implementations • 22 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.
no code implementations • 22 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.
no code implementations • 22 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.
no code implementations • 11 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.
no code implementations • 9 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.
1 code implementation • 8 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.
no code implementations • 2 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.
no code implementations • 31 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.
1 code implementation • 25 Jan 2022 • Mariel 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.
no code implementations • 21 Jan 2022 • Koulik Khamaru, Eric Xia, Martin J. Wainwright, Michael I. Jordan
As a consequence, we propose a data-dependent stopping rule for instance-optimal algorithms.
no code implementations • 21 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.
no code implementations • 29 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.
1 code implementation • 29 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.
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.
no code implementations • 27 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.
no code implementations • 27 Dec 2021 • Tatjana Chavdarova, Michael I. Jordan, Manolis Zampetakis
However, the convergence properties of these methods are qualitatively different, even on simple bilinear games.
no code implementations • 14 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.
1 code implementation • 11 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.
no code implementations • 8 Nov 2021 • Aldo Pacchiano, Peter Bartlett, Michael I. Jordan
We study the problem of information sharing and cooperation in Multi-Player Multi-Armed bandits.
no code implementations • 26 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.
1 code implementation • 20 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.
no code implementations • 12 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.
1 code implementation • 3 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.
no code implementations • 1 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.
1 code implementation • 8 Sep 2021 • Yixin Wang, Michael I. Jordan
Representation learning constructs low-dimensional representations to summarize essential features of high-dimensional data.
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.
no code implementations • 23 Jul 2021 • Guilherme França, Alessandro Barp, Mark Girolami, Michael I. Jordan
Optimization tasks are crucial in statistical machine learning.
no code implementations • 19 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.
no code implementations • 17 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.
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.
no code implementations • 8 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.
no code implementations • 30 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.
no code implementations • 30 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.
no code implementations • 28 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.
no code implementations • 28 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.
no code implementations • 23 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.
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.
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.
no code implementations • 17 Jun 2021 • Feng Ruan, Keli Liu, Michael I. Jordan
Kernel-based feature selection is an important tool in nonparametric statistics.
no code implementations • 11 Jun 2021 • Wenshuo Guo, Kirthevasan Kandasamy, Joseph E Gonzalez, Michael I. Jordan, Ion Stoica
The allocations at a CE are Pareto efficient and fair.
no code implementations • 6 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).
no code implementations • NeurIPS 2021 • Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
We study a theory of reinforcement learning (RL) in which the learner receives binary feedback only once at the end of an episode.
no code implementations • 21 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.
no code implementations • 27 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.
no code implementations • 30 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.
no code implementations • 27 Mar 2021 • Tyler Westenbroek, Max Simchowitz, Michael I. Jordan, S. Shankar Sastry
Crucially, this guarantee requires that state costs applied to the planning problems are in a certain sense `compatible' with the global geometry of the system, and a simple counter-example demonstrates the necessity of this condition.
no code implementations • 24 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.
1 code implementation • 5 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.
no code implementations • NeurIPS 2021 • Xiaowu Dai, Michael I. Jordan
Matching markets are often organized in a multi-stage and decentralized manner.
1 code implementation • 11 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.
2 code implementations • NeurIPS 2021 • Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael I. Jordan
In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control.
3 code implementations • 7 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.
no code implementations • 28 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.
no code implementations • 14 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.
no code implementations • 24 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 $n, d,\delta$.
no code implementations • 9 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.
1 code implementation • 7 Nov 2020 • Karl Krauth, Sarah Dean, Alex Zhao, Wenshuo Guo, Mihaela Curmei, Benjamin Recht, Michael I. Jordan
We observe that offline metrics are correlated with online performance over a range of environments.
no code implementations • 31 Oct 2020 • Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica, Michael I. Jordan, Ken Goldberg, Joseph E. Gonzalez
Second, we present an algorithm for a fixed deadline setting, where we are given a time deadline and need to maximize the probability of finding the best arm.
no code implementations • 31 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.
no code implementations • 29 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.
no code implementations • 25 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.
no code implementations • 23 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.
1 code implementation • 19 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.
2 code implementations • 1 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.