Shubhada Agrawal
8 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(19)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
multi-armed bandit
(4)
regret bound
(3)
heavy-tailed distribution
(3)
stochastic optimization
(3)
best arm identification
(2)
concentration inequality
(2)
sample complexity
(2)
asymptotic variance
(1)
universal portfolio
(1)
temporal difference
(1)
online algorithm
(1)
optimization algorithm
(1)
fluid dynamics
(1)
information-theoretic bound
(1)
robust algorithm
(1)
conditional value at risk
(1)
sub-gaussian mixture
(1)
linear stochastic approximation
(1)
poisson equation
(1)
anytime-valid inference
(1)
Papers
Almost sure null bankruptcy of testing-by-betting strategies
COLT 2026
Eventually LIL Regret: Almost Sure $\ln\ln T$ Regret for a sub-Gaussian Mixture on Unbounded Data
ALT 2026
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption
ALT 2024
Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
NeurIPS 2024
Policy Evaluation for Variance in Average Reward Reinforcement Learning
ICML 2024
Optimal Best-Arm Identification Methods for Tail-Risk Measures
NeurIPS 2021
Regret Minimization in Heavy-Tailed Bandits
COLT 2021
Optimal $δ$-Correct Best-Arm Selection for Heavy-Tailed Distributions
ALT 2020