Prateek Varshney

4 papers · 2020–2024 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

AISTATS (1) COLT (1) NeurIPS (1) SemEval (1)

Top co-authors

Prateek Jain (2) Soumyabrata Pal (2) Abhradeep Thakurta (2) Sandeep Routray (1) Gaurav Aggarwal (1) Soumya Ranjan Dash (1) Gagan Madan (1) Gaurav Srivastava (1) Aniket Das (1) Ashutosh Modi (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Application Areas (2) Core Methods (2) Optimization & Theory (2) Deep Learning (1) Mathematics & Optimization (1) Security & Privacy (1) Architectures (1) Core AI (1) Differential Privacy (1) Learning Paradigms (1) Learning Types (1) Optimization (1)

Keywords

differential privacy (2) stochastic gradient descent (2) convex optimization (1) natural language inference (1) sample complexity (1) low-rank decomposition (1) statistical estimation (1) linear regression (1) alternating minimization (1) stochastic convex optimization (1) streaming algorithm (1) heavy-tailed distribution (1) gradient clipping (1) transformer neural network (1) commonsense reasoning (1) sub-gaussian distribution (1) user personalization (1) martingale concentration (1) heavy-tailed statistical estimation (1) sub-gaussian rate (1)

Papers

Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD NeurIPS 2024 Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components AISTATS 2024 (Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping COLT 2022 CS-NET at SemEval-2020 Task 4: Siamese BERT for ComVE SemEval 2020