Rohan Deb
6 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(5)
🐝
Cross-Pollinator
(13)
🌉
Interdisciplinary Bridge
🐣
Hot Topic Early Bird
❓
The Questioner
Conferences
ICLR (2)
AAAI (1)
AISTATS (1)
ICML (1)
UAI (1)
Top co-authors
Keywords
momentum method
(2)
reinforcement learning
(1)
stochastic gradient descent
(1)
temporal difference learning
(1)
policy evaluation
(1)
online learning
(1)
preference learning
(1)
convergence analysis
(1)
sample complexity
(1)
stochastic approximation
(1)
exp3 algorithm
(1)
quadratic optimization
(1)
regret bound
(1)
budget constraint
(1)
resource consumption
(1)
dueling bandit
(1)
resource constraint
(1)
gradient temporal difference
(1)
stochastic optimization
(1)
heavy ball
(1)
Papers
Conservative Contextual Bandits: Beyond Linear Representations
ICLR 2025
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
ICML 2025
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources
AISTATS 2024
Contextual Bandits with Online Neural Regression
ICLR 2024
Does Momentum Help in Stochastic Optimization? A Sample Complexity Analysis.
UAI 2023
Gradient Temporal Difference with Momentum: Stability and Convergence
AAAI 2022