Avrajit Ghosh

4 papers · 2023–2025 · 3 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ICLR (2) ACL (1) ICML (1)

Top co-authors

Rongrong Wang (4) Xitong Zhang (3) Qing Qu (2) Saiprasad Ravishankar (2) Milad Afshari (1) Soo Min Kwon (1) Guangliang Liu (1) He Lyu (1) Bidhan Bashyal (1) Zhiyu Xue (1)

Research topics

Deep Learning (4) Machine Learning (2) Optimization & Theory · Deep Learning (2) Artificial Intelligence (1) Computer Vision (1) Application Areas (1) Architectures (1) Core AI (1) Generation (1) Learning Types (1) Models (1) Optimization & Theory · Machine Learning (1)

Keywords

stochastic gradient descent (1) neural network optimization (1) gradient descent (1) implicit regularization (1) pre-trained language model (1) image prior (1) generalization performance (1) social bia (1) deep matrix factorization (1) edge of stability (1) model fairness (1) forgetting problem (1) heavy ball momentum (1) bias debiasing (1) task-agnostic debiasing (1) bias relearning (1) loss oscillation (1) overfitting (1) pruning (1) masking (1)

Papers

Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability ICLR 2025 Optimal Eye Surgeon: Finding image priors through sparse generators at initialization ICML 2024 Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness ACL 2024 Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent ICLR 2023