Aditya Krishna Menon

24 papers · 2014–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (9) 🏃 Academic Marathon (11) 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (25) 🧭 Keyword Pioneer 🤝 Dynamic Duo (15) ❓ The Questioner (2) ⚡ Prolific Year (8) 🚀 Conference Pioneer 💎 Century Club (24) 🔥 Unstoppable (7)

Conferences

ICLR (14) ICML (2) JMLR (2) AAAI (1) COLT (1) CVPR (1) EMNLP (1) IJCAI (1) UAI (1)

Top co-authors

Sanjiv Kumar (15) Ankit Singh Rawat (9) Harikrishna Narasimhan (8) Wittawat Jitkrittum (6) MICHAL LUKASIK (4) Neha Gupta (3) Seungyeon Kim (3) Sashank J. Reddi (2) Robert C. Williamson (2) Andreas Veit (2)

Keywords

proper loss (2) bipartite ranking (2) binary classification (1) bayesian inference (1) gradient-based optimization (1) model calibration (1) extractive summarization (1) stochastic process (1) document summarization (1) maximum likelihood (1) bregman divergence (1) risk minimization (1) label noise (1) point process (1) roc curve (1) knowledge distillation (1) maximum mean discrepancy (1) poisson process (1) bayes optimal (1) bayesian learning (1)

Papers

Faster Cascades via Speculative Decoding ICLR 2025

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation ICML 2025

Better autoregressive regression with LLMs via regression-aware fine-tuning ICLR 2025

Regression Aware Inference with LLMs EMNLP 2024

The importance of feature preprocessing for differentially private linear optimization ICLR 2024

DistillSpec: Improving Speculative Decoding via Knowledge Distillation ICLR 2024

Think before you speak: Training Language Models With Pause Tokens ICLR 2024

Plugin estimators for selective classification with out-of-distribution detection ICLR 2024

Learning to Reject Meets Long-tail Learning ICLR 2024

Language Model Cascades: Token-Level Uncertainty And Beyond ICLR 2024

USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval ICML 2024

Robust distillation for worst-class performance: on the interplay between teacher and student objectives UAI 2023

Supervision Complexity and its Role in Knowledge Distillation ICLR 2023

Interval-censored Hawkes processes JMLR 2022

Long-tail learning via logit adjustment ICLR 2021

Overparameterisation and worst-case generalisation: friend or foe? ICLR 2021

Coping with Label Shift via Distributionally Robust Optimisation ICLR 2021

Can gradient clipping mitigate label noise? ICLR 2020

Comparative Document Summarisation via Classification AAAI 2019

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data ICLR 2019

Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach CVPR 2017

Practical Linear Models for Large-Scale One-Class Collaborative Filtering IJCAI 2016

Bipartite Ranking: a Risk-Theoretic Perspective JMLR 2016

Bayes-Optimal Scorers for Bipartite Ranking COLT 2014