Aravind Gollakota
8 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
NIPS (5)
ICLR (2)
ICML (1)
Top co-authors
Keywords
learning theory
(3)
lower bound
(2)
agnostic learning
(2)
relu activation
(2)
neural network
(2)
bregman divergence
(1)
label noise
(1)
gradient descent
(1)
poincare inequality
(1)
distribution testing
(1)
halfspace classification
(1)
generative model
(1)
diffusion model
(1)
gaussian input
(1)
compressed sensing
(1)
single-index model
(1)
log-concave distribution
(1)
relu network
(1)
sum-of-squares program
(1)
corrupted datum
(1)
Papers
Provable Uncertainty Decomposition via Higher-Order Calibration
ICLR 2025
An Efficient Tester-Learner for Halfspaces
ICLR 2024
Ambient Diffusion: Learning Clean Distributions from Corrupted Data
NIPS 2023
Tester-Learners for Halfspaces: Universal Algorithms
NIPS 2023
Agnostically Learning Single-Index Models using Omnipredictors
NIPS 2023
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
NIPS 2022
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent
ICML 2020
Statistical-Query Lower Bounds via Functional Gradients
NIPS 2020