Gaurav Mahajan
13 papers · 2020–2026 · 6 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£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (26)
ποΈ
Keyword Collector
(78)
π
Trend Setter
π
Century Club Β· Bronze
β
The Questioner
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Machine Learning
(13)
Optimization & Theory
(12)
Learning Types
(7)
Reinforcement Learning
(6)
Methods
(5)
Core Methods
(4)
Data Science & Analytics
(2)
Mathematics & Optimization
(2)
Optimization
(2)
Artificial Intelligence
(1)
Computer Science
(1)
Interdisciplinary
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Core AI
(1)
Keywords
sample complexity
(5)
reinforcement learning
(3)
function approximation
(3)
global convergence
(2)
computational complexity
(2)
linear function approximation
(2)
computational-statistical gaps
(2)
computational lower bound
(2)
markov decision process
(2)
pac learning
(2)
density estimation
(1)
natural policy gradient
(1)
convergence analysis
(1)
online learning
(1)
reinforcement learning theory
(1)
sample efficiency
(1)
probability distribution
(1)
policy gradient
(1)
uniform convergence
(1)
k-means clustering
(1)
Papers
Cloning is as Hard as Learning for Stabilizer States
COLT 2026
Do PAC-Learners Learn the Marginal Distribution?
ALT 2025
Exponential Hardness of Reinforcement Learning with Linear Function Approximation
COLT 2023
Learning Hidden Markov Models Using Conditional Samples
COLT 2023
Computational-Statistical Gap in Reinforcement Learning
COLT 2022
Convergence of online k-means
AISTATS 2022
Learning what to remember
ALT 2022
Realizable Learning is All You Need
COLT 2022
Bilinear Classes: A Structural Framework for Provable Generalization in RL
ICML 2021
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
JMLR 2021
Agnostic Q-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity
NeurIPS 2020
Noise-tolerant, Reliable Active Classification with Comparison Queries
COLT 2020
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes
COLT 2020