Karthik Abinav Sankararaman

15 papers · 2018–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) 🏃 Academic Marathon (7) 🐝 Cross-Pollinator (7) 🌈 Renaissance Researcher (6) 🗺️ Taxonomy Completionist (22) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 👥 Mega-Team (21) 🚀 Conference Pioneer 🗃️ Keyword Collector (55) 💎 Century Club (15) ❓ The Questioner

Conferences

ICML (4) AISTATS (3) AAAI (2) NIPS (2) ACL (1) COLT (1) JMLR (1) NAACL (1)

Top co-authors

Aleksandrs Slivkins (4) Han Fang (3) Pan Xu (3) Aravind Srinivasan (3) Hao Ma (3) Sinong Wang (3) Abishek Sankararaman (2) Wenxuan Zhou (2) Eryk Helenowski (2) Tengyu Xu (2)

Keywords

multi-armed bandit (5) regret bound (3) contextual bandit (3) combinatorial optimization (2) lagrangian approach (2) online matching (2) packing constraint (2) knapsack problem (2) regression oracle (2) covering constraint (2) online learning (2) large language model (2) decentralized algorithm (2) vanishing regret (2) thompson sampling (1) lagrangian relaxation (1) bipartite matching (1) resource allocation (1) linear programming (1) batch normalization (1)

Papers

Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization ICML 2025

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation ACL 2025

Effective Long-Context Scaling of Foundation Models NAACL 2024

Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression JMLR 2024

Promoting External and Internal Equities Under Ex-Ante/Ex-Post Metrics in Online Resource Allocation ICML 2024

Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression COLT 2023

Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial? NIPS 2023

Multi-Armed Bandits with Cost Subsidy AISTATS 2021

Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship AISTATS 2021

Bandits with Knapsacks beyond the Worst Case NIPS 2021

Beyond $log^2(T)$ regret for decentralized bandits in matching markets ICML 2021

The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent ICML 2020

A Unified Approach to Online Matching with Conflict-Aware Constraints AAAI 2019

Balancing Relevance and Diversity in Online Bipartite Matching via Submodularity AAAI 2019

Combinatorial Semi-Bandits with Knapsacks AISTATS 2018