Karampatziakis, Nikos

17 publications

NeurIPS 2024 Active, Anytime-Valid Risk Controlling Prediction Sets Ziyu Xu, Nikos Karampatziakis, Paul Mineiro

ICLR 2024 LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models Yixiao Li, Yifan Yu, Chen Liang, Nikos Karampatziakis, Pengcheng He, Weizhu Chen, Tuo Zhao

NeurIPSW 2023 HART: Efficient Adaptation via Regularized Autoregressive Parameter Generation Chen Liang, Nikos Karampatziakis, Tuo Zhao, Weizhu Chen

NeurIPS 2023 Meet in the Middle: A New Pre-Training Paradigm Anh Nguyen, Nikos Karampatziakis, Weizhu Chen

ICML 2021 Off-Policy Confidence Sequences Nikos Karampatziakis, Paul Mineiro, Aaditya Ramdas

NeurIPS 2020 Empirical Likelihood for Contextual Bandits Nikos Karampatziakis, John Langford, Paul Mineiro

ICMLW 2019 Lessons from Contextual Bandit Learning in a Customer Support Bot Nikos Karampatziakis, Sebastian Kochman, Jade Huang, Paul Mineiro, Kathy Osborne, Weizhu Chen

ICML 2017 Gradient Coding: Avoiding Stragglers in Distributed Learning Rashish Tandon, Qi Lei, Alexandros G. Dimakis, Nikos Karampatziakis

ICML 2017 Logarithmic Time One-Against-Some Hal Daumé, Nikos Karampatziakis, John Langford, Paul Mineiro

ICLR 2015 Fast Label Embeddings for Extremely Large Output Spaces Paul Mineiro, Nikos Karampatziakis

ECML-PKDD 2015 Fast Label Embeddings via Randomized Linear Algebra Paul Mineiro, Nikos Karampatziakis

ICML 2014 Discriminative Features via Generalized Eigenvectors Nikos Karampatziakis, Paul Mineiro

ICML 2014 Least Squares Revisited: Scalable Approaches for Multi-Class Prediction Alekh Agarwal, Sham Kakade, Nikos Karampatziakis, Le Song, Gregory Valiant

ICML 2013 Loss-Proportional Subsampling for Subsequent ERM Paul Mineiro, Nikos Karampatziakis

UAI 2011 Efficient Optimal Learning for Contextual Bandits Miroslav Dudík, Daniel J. Hsu, Satyen Kale, Nikos Karampatziakis, John Langford, Lev Reyzin, Tong Zhang

UAI 2011 Online Importance Weight Aware Updates Nikos Karampatziakis, John Langford

NeurIPS 2010 Static Analysis of Binary Executables Using Structural SVMs Nikos Karampatziakis