Arun Sai Suggala
I’m broadly interested in online learning, game theory, and their applications to reliable and robust machine learning.
Research Areas
Authored Publications
Sort By
Online Bidding under RoS Constraints without Knowing the Value
Sushant Vijayan
Swati Padmanabhan
The Web Conference (2025)
Preview abstract
We consider the problem of auto-bidding in online advertising from the perspective of a single advertiser. The goal of the advertiser is to maximize their value under the Return-on-Spend (RoS) constraint, with performance measured in terms of \emph{regret} against the optimal offline solution that knows all queries a priori. Importantly, the value of the item is \textit{unknown} to the bidder ahead of time. The goal of the bidder is to quickly identify the optimal bid, while simultaneously satisfying budget and RoS constraints. Using a simple UCB-style algorithm, we provide the first result which achieves optimal regret and constraint violation for this problem.
View details
Preview abstract
Learned reweighting (LRW) approaches to supervised learning use an optimization criterion to assign weights for training instances, in order to maximize performance on a representative validation dataset. We pose and formalize the problem of optimized selection of the validation set used in LRW training, to improve classifier generalization. In particular, we show that using hard-to-classify instances in the validation set has both a theoretical connection to, and strong empirical evidence of generalization. We provide an efficient algorithm for training this meta-optimized model, as well as a simple train-twice heuristic for careful comparative study. We demonstrate that LRW with easy validation data performs consistently worse than LRW with hard validation data, establishing the validity of our meta-optimization problem. Our proposed algorithm outperforms a wide range of baselines on a range of datasets and domain shift challenges (Imagenet-1K, CIFAR-100, Clothing-1M, CAMELYON, WILDS, etc.), with ~1% gains using VIT-B on Imagenet. We also show that using naturally hard examples for validation (Imagenet-R / Imagenet-A) in LRW training for Imagenet improves performance on both clean and naturally hard test instances by 1-2%. Secondary analyses show that using hard validation data in an LRW framework improves margins on test data, hinting at the mechanism underlying our empirical gains. We believe this work opens up new research directions for the meta-optimization of meta-learning in a supervised learning context.
View details
Evaluating PEARL - a Personalized Exercise Assistant using Reinforcement Learning (Walkmate Study)
Hulya Emir-Farinas
Martin Seneviratne
Amy Lee
Jim Taylor
Sriram Lakshminarasimhan
Emily Rosenzweig
OSF Registries (2024)
Preview abstract
Study protocol for PEARL Study: To evaluate the impact of two personalized nudging strategies delivered as pop-up notifications via the Fitbit app on user step count. Specifically, to personalize the following parameters of the pop-up notification system: message content, and timing (hr of the day)
View details
Preview abstract
We consider the problem of latent bandits with cluster structure where there are multiple users, each with an associated multi-armed bandit problem. These users are grouped into \emph{latent} clusters such that the mean reward vectors of users within the same cluster are identical. At each round, a user, selected uniformly at random, pulls an arm and observes a corresponding noisy reward. The goal of the users is to maximize their cumulative rewards. This problem is central to practical recommendation systems and has received wide attention of late \cite{gentile2014online, maillard2014latent}. Now, if each user acts independently, then they would have to explore each arm independently and a regret of $Ω(\sqrt{MNT})$ is unavoidable, where ?,? are the number of arms and users, respectively. Instead, we propose LATTICE (Latent bAndiTs via maTrIx ComplEtion) which allows exploitation of the latent cluster structure to provide the minimax optimal regret of $\tilde{O}(\sqrt{(M+N)T})$, when the number of clusters is $\tilde{O}(1)$. This is the first algorithm to guarantee such strong regret bound. LATTICE is based on a careful exploitation of arm information within a cluster while simultaneously clustering users. Furthermore, it is computationally efficient and requires only O(log?) calls to an offline matrix completion oracle across all ? rounds.
View details
Preview abstract
We consider the problem of \emph{blocked} collaborative bandits where there are multiple users, each with an associated multi-armed bandit problem. These users are grouped into \emph{latent} clusters such that the mean reward vectors of users within the same cluster are identical. Our goal is to design algorithms that maximize the cumulative reward accrued by all the users over time, under the \emph{constraint} that no arm of a user is pulled more than ? times. This problem has been originally considered by \cite{Bresler:2014}, and designing regret-optimal algorithms for it has since remained an open problem. In this work, we propose an algorithm called \texttt{B-LATTICE} (Blocked Latent bAndiTs via maTrIx ComplEtion) that collaborates across users, while simultaneously satisfying the budget constraints, to maximize their cumulative rewards. Theoretically, under certain reasonable assumptions on the latent structure, with M users, N arms, T rounds per user, and C=O(1) latent clusters, \texttt{B-LATTICE} achieves a per-user regret of $\tilde{O}(\sqrt{T(1+N/M)})$ under a budget constraint of B=Θ(log T). These are the first sub-linear regret bounds for this problem, and match the minimax regret bounds when B=T. Empirically, we demonstrate that our algorithm has superior performance over baselines even when B=1. \texttt{B-LATTICE} runs in phases where in each phase it clusters users into groups and collaborates across users within a group to quickly learn their reward models.
View details
Building Robust Ensembles via Margin Boosting
Aaron Courville
Dinghuai Zhang
Hongyang Zhang
Pradeep Ravikumar
Yoshua Bengio
International Conference on Machine Learning (2022)
Preview abstract
In the context of adversarial robustness, a single model does not usually have enough power to defend against all possible adversarial attacks, and as a result, has sub-optimal robustness. Consequently, an emerging line of work has focused on learning an ensemble of neural networks to defend against adversarial attacks. In this work, we take a principled approach towards building robust ensembles. We view this problem from the perspective of margin-boosting and develop an algorithm for learning an ensemble with maximum margin. Through extensive empirical evaluation on benchmark datasets, we show that our algorithm not only outperforms existing ensembling techniques, but also large models trained in an end-to-end fashion. An important byproduct of our work is a margin-maximizing cross-entropy (MCE) loss, which is a better alternative to the standard cross-entropy (CE) loss. Empirically, we show that replacing the CE loss in state-of-the-art adversarial training techniques with our MCE loss leads to significant performance improvement.
View details
