Valentin Thomas
6 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4) π Academic Marathon (5)
π
Cross-Pollinator
(13)
πΊοΈ
Taxonomy Completionist
(14)
Conferences
NIPS (3)
AISTATS (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
natural policy gradient
(2)
variance reduction
(2)
stochastic gradient descent
(1)
temporal difference learning
(1)
policy optimization
(1)
in-context learning
(1)
convergence analysis
(1)
fisher information
(1)
nearest neighbor
(1)
off-policy learning
(1)
linear function approximation
(1)
hessian matrix
(1)
random matrix theory
(1)
multi-armed bandit
(1)
bandit problem
(1)
learning dynamics
(1)
generalization gap
(1)
tabular datum
(1)
gradient variance
(1)
retrieval augmentation
(1)
Papers
Retrieval & Fine-Tuning for In-Context Tabular Models
NIPS 2024
The Role of Baselines in Policy Gradient Optimization
NIPS 2022
On the role of overparameterization in off-policy Temporal Difference learning with linear function approximation
NIPS 2022
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
ICML 2021
On the interplay between noise and curvature and its effect on optimization and generalization
AISTATS 2020
Probabilistic Planning with Sequential Monte Carlo methods
ICLR 2019