3 citations · 11 across the 15 of their papers we have counts for
17 papers
Data Deletion Can Help in Adaptive RL
Param Budhraja, Aditya Gangrade, Alex Olshevsky +1
Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) f…
Linear Transformers Implicitly Discover Unified Numerical Algorithms
Patrick Lutz, Aditya Gangrade, Hadi Daneshmand +1
We train a linear attention transformer on millions of masked-block matrix completion tasks: each prompt is masked low-rank matrix whose missing block may be (i) a scalar predictio…
Constrained Linear Thompson Sampling
Aditya Gangrade, Venkatesh Saligrama
We study safe linear bandits (SLBs), where an agent selects actions from a convex set to maximize an unknown linear objective subject to unknown linear constraints in each round. E…
SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
Kevin Miller, Samarth Mishra, Aditya Gangrade +2
Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existin…
Testing the Feasibility of Linear Programs with Bandit Feedback
Aditya Gangrade, Aditya Gopalan, Venkatesh Saligrama +1
While the recent literature has seen a surge in the study of constrained bandit problems, all existing methods for these begin by assuming the feasibility of the underlying problem…
Counterfactually Comparing Abstaining Classifiers
Yo Joong Choe, Aditya Gangrade, Aaditya Ramdas
Abstaining classifiers have the option to abstain from making predictions on inputs that they are unsure about. These classifiers are becoming increasingly popular in high-stakes d…
A Sequential Test for Log-Concavity
Aditya Gangrade, Alessandro Rinaldo, Aaditya Ramdas
On observing a sequence of i.i.d.\ data with distribution on , we ask the question of how one can test the null hypothesis that has a log-concave density. Thi…
Safe Linear Bandits over Unknown Polytopes
Aditya Gangrade, Tianrui Chen, Venkatesh Saligrama
The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints, under stochastic bandit feedback of rewar…
Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
Tianrui Chen, Aditya Gangrade, Venkatesh Saligrama
We investigate a natural but surprisingly unstudied approach to the multi-armed bandit problem under safety risk constraints. Each arm is associated with an unknown law on safety r…
Universal Inference Meets Random Projections: A Scalable Test for Log-concavity
Robin Dunn, Aditya Gangrade, Larry Wasserman +1
Shape constraints yield flexible middle grounds between fully nonparametric and fully parametric approaches to modeling distributions of data. The specific assumption of log-concav…
Online Selective Classification with Limited Feedback
Aditya Gangrade, Anil Kag, Ashok Cutkosky +1
Motivated by applications to resource-limited and safety-critical domains, we study selective classification in the online learning model, wherein a predictor may abstain from clas…
Limits on Testing Structural Changes in Ising Models
Aditya Gangrade, Bobak Nazer, Venkatesh Saligrama
We present novel information-theoretic limits on detecting sparse changes in Ising models, a problem that arises in many applications where network changes can occur due to some ex…
Selective Classification via One-Sided Prediction
Aditya Gangrade, Anil Kag, Venkatesh Saligrama
We propose a novel method for selective classification (SC), a problem which allows a classifier to abstain from predicting some instances, thus trading off accuracy against covera…
Piecewise Linear Regression via a Difference of Convex Functions
Ali Siahkamari, Aditya Gangrade, Brian Kulis +1
We present a new piecewise linear regression methodology that utilizes fitting a difference of convex functions (DC functions) to the data. These are functions that may be repr…
Budget Learning via Bracketing
Aditya Gangrade, Durmus Alp Emre Acar, Venkatesh Saligrama
Conventional machine learning applications in the mobile/IoT setting transmit data to a cloud-server for predictions. Due to cost considerations (power, latency, monetary), it is d…
Testing Changes in Communities for the Stochastic Block Model
Aditya Gangrade, Praveen Venkatesh, Bobak Nazer +1
We propose and analyze the problems of \textit{community goodness-of-fit and two-sample testing} for stochastic block models (SBM), where changes arise due to modification in commu…
Lower Bounds for Two-Sample Structural Change Detection in Ising and Gaussian Models
Aditya Gangrade, Bobak Nazer, Venkatesh Saligrama
The change detection problem is to determine if the Markov network structures of two Markov random fields differ from one another given two sets of samples drawn from the respectiv…