Teodor Vanislavov Marinov
14 papers · 2017–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (20) π§ Keyword Pioneer π Conference Polyglot (5) π Academic Marathon (8)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
π
Century Club
(13)
ποΈ
Keyword Collector
(54)
Conferences
NIPS (8)
ALT (2)
ICML (2)
AISTATS (1)
COLT (1)
Top co-authors
Keywords
regret bound
(5)
principal component analysis
(3)
streaming algorithm
(3)
multi-armed bandit
(3)
feedback graph
(3)
online learning
(2)
game theory
(1)
outlier detection
(1)
reinforcement learning
(1)
sample complexity
(1)
in-context learning
(1)
kernel pca
(1)
value function
(1)
convex relaxation
(1)
model selection
(1)
stochastic process
(1)
stochastic approximation
(1)
matrix factorization
(1)
sparse linear regression
(1)
exploration exploitation
(1)
Papers
Efficient Opportunistic Approachability
ALT 2026
Design Considerations in Offline Preference-based RL
ICML 2025
A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks
ALT 2024
Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
NIPS 2022
Open Problem: Finite-Time Instance Dependent Optimality for Stochastic Online Learning with Feedback Graphs
COLT 2022
Corralling Stochastic Bandit Algorithms
AISTATS 2021
The Pareto Frontier of model selection for general Contextual Bandits
NIPS 2021
Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
NIPS 2021
Efficient Convex Relaxations for Streaming PCA
NIPS 2019
Bandits with Feedback Graphs and Switching Costs
NIPS 2019
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features
NIPS 2018
Streaming Principal Component Analysis in Noisy Setting
ICML 2018
Policy Regret in Repeated Games
NIPS 2018
Stochastic Approximation for Canonical Correlation Analysis
NIPS 2017