Dhruv Rohatgi
16 papers · 2020–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (28) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(87)
Venues
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory
(11)
Core Methods
(7)
Mathematics & Optimization
(6)
Artificial Intelligence
(5)
Core AI
(5)
Learning Types
(5)
Optimization
(4)
Deep Learning
(3)
Reinforcement Learning
(2)
Mathematics
(2)
Methods
(2)
Computer Science
(1)
Architectures
(1)
Foundations
(1)
Keywords
sparse linear regression
(3)
compressed sensing
(3)
robust statistics
(1)
reinforcement learning theory
(1)
reinforcement learning from human feedback
(1)
sample complexity
(1)
policy learning
(1)
partially observable markov decision process
(1)
computational efficiency
(1)
high-dimensional statistics
(1)
minimax optimality
(1)
outlier detection
(1)
maximum likelihood
(1)
covariance matrix
(1)
stochastic gradient descent
(1)
exponential family
(1)
linear regression
(1)
robust estimation
(1)
signal recovery
(1)
sparse recovery
(1)
Papers
Steering diffusion models with quadratic rewards: a fine-grained analysis
COLT 2026
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract)
COLT 2025
Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
COLT 2025
Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning
COLT 2025
Self-Improvement in Language Models: The Sharpening Mechanism
ICLR 2025
Towards characterizing the value of edge embeddings in Graph Neural Networks
ICML 2025
Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps
COLT 2024
Online Control in Population Dynamics
NeurIPS 2024
Feature Adaptation for Sparse Linear Regression
NeurIPS 2023
Provable benefits of score matching
NeurIPS 2023
Provably Auditing Ordinary Least Squares in Low Dimensions
ICLR 2023
Learning in Observable POMDPs, without Computationally Intractable Oracles
NeurIPS 2022
Lower Bounds on Randomly Preconditioned Lasso via Robust Sparse Designs
NeurIPS 2022
Robust Generalized Method of Moments: A Finite Sample Viewpoint
NeurIPS 2022
Constant-Expansion Suffices for Compressed Sensing with Generative Priors
NeurIPS 2020
Truncated Linear Regression in High Dimensions
NeurIPS 2020