ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Surya Ganguli

Surya Ganguli

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 3:11 AM AMS

12

papers

2,408

total citations

papers (12)

Pruning neural networks without any data by iteratively conserving synaptic flow

NEURIPS 2020arXiv

Deep Learning on a Data Diet: Finding Important Examples Early in Training

NEURIPS 2021arXiv

Beyond neural scaling laws: beating power law scaling via data pruning

NEURIPS 2022arXiv

Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel

NEURIPS 2020arXiv

Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression

NEURIPS 2023arXiv

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks

NEURIPS 2023arXiv

Predictive coding in balanced neural networks with noise, chaos and delays

NEURIPS 2020arXiv

Identifying Learning Rules From Neural Network Observables

NEURIPS 2020arXiv

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks

NEURIPS 2022arXiv

Features are fate: a theory of transfer learning in high-dimensional regression

Information Geometry of the Retinal Representation Manifold

Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks