Dheeraj Nagaraj
16 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (23) π Conference Polyglot (5)
π
Academic Marathon
(7)
π
Cross-Pollinator
(13)
π
Century Club
(16)
ποΈ
Keyword Collector
(76)
Conferences
NIPS (9)
COLT (4)
AISTATS (1)
ICML (1)
IJCAI (1)
Top co-authors
Keywords
stochastic gradient descent
(6)
streaming algorithm
(3)
experience replay
(3)
convex optimization
(2)
resource allocation
(2)
ising model
(1)
transfer learning
(1)
zero-shot learning
(1)
sample complexity
(1)
automated planning
(1)
deep learning theory
(1)
fourier analysis
(1)
variational inference
(1)
hypothesis testing
(1)
hierarchical learning
(1)
statistical estimation
(1)
gradient descent
(1)
mean field
(1)
reward function
(1)
bayesian inference
(1)
Papers
Beyond propagation of chaos: A stochastic algorithm for mean field optimization
COLT 2025
Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization
IJCAI 2024
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
NIPS 2024
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
NIPS 2024
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
NIPS 2024
Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
AISTATS 2023
Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
NIPS 2023
Streaming Linear System Identification with Reverse Experience Replay
NIPS 2021
Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems
NIPS 2021
The staircase property: How hierarchical structure can guide deep learning
NIPS 2021
A Corrective View of Neural Networks: Representation, Memorization and Learning
COLT 2020
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms
NIPS 2020
Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth
NIPS 2020
Making the Last Iterate of SGD Information Theoretically Optimal
COLT 2019
SGD without Replacement: Sharper Rates for General Smooth Convex Functions
ICML 2019
Optimal Single Sample Tests for Structured versus Unstructured Network Data
COLT 2018