More Like this

1. On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

   Anagnostides, I; Panageas, I; Farina, G; Sandholm, T (December 2023, NeurIPS23)

   Most of the literature on learning in games has focused on the restrictive setting where the underlying repeated game does not change over time. Much less is known about the convergence of no-regret learning algorithms in dynamic multiagent settings. In this paper, we characterize the convergence of optimistic gradient descent (OGD) in time-varying games. Our framework yields sharp convergence bounds for the equilibrium gap of OGD in zero-sum games parameterized on natural variation measures of the sequence of games, subsuming known results for static games. Furthermore, we establish improved second-order variation bounds under strong convexity-concavity, as long as each game is repeated multiple times. Our results also extend to time-varying general-sum multi-player games via a bilinear formulation of correlated equilibria, which has novel implications for meta-learning and for obtaining refined variation-dependent regret bounds, addressing questions left open in prior papers. Finally, we leverage our framework to also provide new insights on dynamic regret guarantees in static games. 1 

   more » « less
2. Conformal Prediction with Learned Features

   Kiyani, Shayan; Pappas, George; Hassani, Hamed (July 2024, ICML)

   In this paper, we focus on the problem of conformal prediction with conditional guarantees. Prior work has shown that it is impossible to construct nontrivial prediction sets with full conditional coverage guarantees. A wealth of research has considered relaxations of full conditional guarantees, relying on some predefined uncertainty structures. Departing from this line of thinking, we propose Partition Learning Conformal Prediction (PLCP), a framework to improve conditional validity of prediction sets through learning uncertainty-guided features from the calibration data. We implement PLCP efficiently with alternating gradient descent, utilizing off-the-shelf machine learning models. We further analyze PLCP theoretically and provide conditional guarantees for infinite and finite sample sizes. Finally, our experimental results over four real-world and synthetic datasets show the superior performance of PLCP compared to state-of-the-art methods in terms of coverage and length in both classification and regression scenarios. 

   more » « less
3. Batch Multivalid Conformal Prediction

   Jung, Christopher; Noarov, Georgy; Ramalingam, Ramya; Roth, Aaron (January 2023, International Conference on Learning Representations (ICLR))

   We develop fast distribution-free conformal prediction algorithms for obtaining multivalid coverage on exchangeable data in the batch setting. Multivalid coverage guarantees are stronger than marginal coverage guarantees in two ways: (1) They hold even conditional on group membership---that is, the target coverage level holds conditionally on membership in each of an arbitrary (potentially intersecting) group in a finite collection of regions in the feature space. (2) They hold even conditional on the value of the threshold used to produce the prediction set on a given example. In fact multivalid coverage guarantees hold even when conditioning on group membership and threshold value simultaneously. We give two algorithms: both take as input an arbitrary non-conformity score and an arbitrary collection of possibly intersecting groups , and then can equip arbitrary black-box predictors with prediction sets. Our first algorithm is a direct extension of quantile regression, needs to solve only a single convex minimization problem, and produces an estimator which has group-conditional guarantees for each group in . Our second algorithm is iterative, and gives the full guarantees of multivalid conformal prediction: prediction sets that are valid conditionally both on group membership and non-conformity threshold. We evaluate the performance of both of our algorithms in an extensive set of experiments. 

   more » « less
4. Online Adaptation to Label Distribution Shift

   Ruihan Wu, Chuan Guo (January 2021, Advances in neural information processing systems)

   Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually changing and the model must dynamically adapt to it without observing the true label. Leverag- ing a novel analysis, we show that the lack of true label does not hinder estimation of the expected test loss, which enables the reduction of online label shift adap- tation to conventional online learning. Informed by this observation, we propose adaptation algorithms inspired by classical online learning techniques such as Fol- low The Leader (FTL) and Online Gradient Descent (OGD) and derive their regret bounds. We empirically verify our findings under both simulated and real world label distribution shifts and show that OGD is particularly effective and robust to a variety of challenging label shift scenarios. 

   more » « less
5. Adaptive data collection for robust learning across multiple distributions

   Zang, Chengbo; Turkcan, Mehme; Zussman, Gil; Kostic, Zoran; Ghaderi, Javad (May 2025, in Proc. ICML’25, 2025)

   We propose a framework for adaptive data collection aimed at robust learning in multi-distribution scenarios under a fixed data collection budget. In each round, the algorithm selects a distribution source to sample from for data collection and updates the model parameters accordingly. The objective is to find the model parameters that minimize the expected loss across all the data sources. Our approach integrates upper-confidence-bound (UCB) sampling with online gradient descent (OGD) to dynamically collect and annotate data from multiple sources. By bridging online optimization and multi-armed bandits, we provide theoretical guarantees for our UCB-OGD approach, demonstrating that it achieves a minimax regret of O(T 1 2 (K ln T) 1 2 ) over K data sources after T rounds. We further provide a lower bound showing that the result is optimal up to a ln T factor. Extensive evaluations on standard datasets and a real-world testbed for object detection in smartcity intersections validate the consistent performance improvements of our method compared to baselines such as random sampling and various active learning methods. 

   more » « less