Dhruv Rohatgi
15 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π Conference Polyglot (4)
π
Academic Marathon
(5)
β‘
Prolific Year
(5)
π
Century Club
(15)
β
The Questioner
Conferences
NIPS (8)
COLT (4)
ICLR (2)
ICML (1)
Top co-authors
Keywords
sparse linear regression
(3)
compressed sensing
(3)
robust statistics
(1)
reinforcement learning theory
(1)
partially observable markov decision process
(1)
computational efficiency
(1)
outlier detection
(1)
score matching
(1)
maximum likelihood
(1)
covariance matrix
(1)
high-dimensional statistics
(1)
exponential family
(1)
robust estimation
(1)
signal recovery
(1)
stochastic gradient descent
(1)
sparse recovery
(1)
phase retrieval
(1)
condition number
(1)
computational-statistical gaps
(1)
causal inference
(1)
Papers
Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
COLT 2025
Towards characterizing the value of edge embeddings in Graph Neural Networks
ICML 2025
Self-Improvement in Language Models: The Sharpening Mechanism
ICLR 2025
Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning
COLT 2025
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract)
COLT 2025
Online Control in Population Dynamics
NIPS 2024
Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps
COLT 2024
Provable benefits of score matching
NIPS 2023
Provably Auditing Ordinary Least Squares in Low Dimensions
ICLR 2023
Feature Adaptation for Sparse Linear Regression
NIPS 2023
Robust Generalized Method of Moments: A Finite Sample Viewpoint
NIPS 2022
Lower Bounds on Randomly Preconditioned Lasso via Robust Sparse Designs
NIPS 2022
Learning in Observable POMDPs, without Computationally Intractable Oracles
NIPS 2022
Constant-Expansion Suffices for Compressed Sensing with Generative Priors
NIPS 2020
Truncated Linear Regression in High Dimensions
NIPS 2020