Niladri S. Chatterji
10 papers · 2018–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (20)
π
Keyword Champion
(3)
ποΈ
Keyword Collector
(50)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory Β· Machine Learning
(10)
Deep Learning
(7)
Optimization & Theory Β· Deep Learning
(5)
Core Methods
(4)
Learning Types
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Architectures
(2)
Resources & Methods
(2)
Mathematics & Optimization
(1)
Bayesian & Probabilistic
(1)
Core AI
(1)
Optimization
(1)
Techniques
(1)
Keywords
excess risk
(3)
benign overfitting
(3)
logistic loss
(3)
gradient descent
(3)
binary classification
(2)
gradient flow
(2)
language model
(2)
markov chain monte carlo
(1)
neural network optimization
(1)
feature learning
(1)
excess risk bound
(1)
linear regression
(1)
minimum norm
(1)
hamiltonian monte carlo
(1)
relu activation
(1)
knowledge distillation
(1)
convergence rate
(1)
generalization bound
(1)
linear classifier
(1)
basis pursuit
(1)
Papers
Compute Optimal Scaling of Skills: Knowledge vs Reasoning
ACL 2025
Proving Test Set Contamination in Black-Box Language Models
ICLR 2024
Deep linear networks can benignly overfit when shallow ones do
JMLR 2023
Random Feature Amplification: Feature Learning and Generalization in Neural Networks
JMLR 2023
Foolish Crowds Support Benign Overfitting
JMLR 2022
The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks
JMLR 2022
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime
JMLR 2021
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks?
JMLR 2021
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
COLT 2021
Underdamped Langevin MCMC: A non-asymptotic analysis
COLT 2018