Eshaan Nichani
11 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (15) π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (12)
π
Century Club
(11)
π
Conference Pioneer
Conferences
ICLR (4)
NIPS (4)
CLEAR (1)
COLT (1)
ICML (1)
Top co-authors
Keywords
sample complexity
(3)
gradient descent
(2)
representation learning
(2)
stochastic gradient descent
(1)
feature learning
(1)
causal discovery
(1)
in-context learning
(1)
neural network optimization
(1)
spectral analysis
(1)
graph structure learning
(1)
clustering algorithm
(1)
latent factor model
(1)
generalization guarantee
(1)
zeroth-order optimization
(1)
low-rank adaptation
(1)
parameter-efficient tuning
(1)
hierarchical feature
(1)
single index model
(1)
language model fine-tuning
(1)
gene regulatory network
(1)
Papers
Learning Compositional Functions with Transformers from Easy-to-Hard Data
COLT 2025
Learning Hierarchical Polynomials of Multiple Nonlinear Features
ICLR 2025
Understanding Factual Recall in Transformers via Associative Memories
ICLR 2025
How Transformers Learn Causal Structure with Gradient Descent
ICML 2024
Learning Hierarchical Polynomials with Three-Layer Neural Networks
ICLR 2024
Fine-Tuning Language Models with Just Forward Passes
NIPS 2023
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
ICLR 2023
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
NIPS 2023
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
NIPS 2023
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
NIPS 2022
Causal Structure Discovery between Clusters of Nodes Induced by Latent Factors
CLEAR 2022