Nakkiran, Preetum

28 publications

ICLR 2025 A Formal Framework for Understanding Length Generalization in Transformers Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn

TMLR 2025 Classifier-Free Guidance Is a Predictor-Corrector Arwen Bradley, Preetum Nakkiran

AISTATS 2025 Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo James Thornton, Louis Béthune, Ruixiang Zhang, Arwen Bradley, Preetum Nakkiran, Shuangfei Zhai

ICML 2025 Mechanisms of Projective Composition of Diffusion Models Arwen Bradley, Preetum Nakkiran, David Berthelot, James Thornton, Joshua M. Susskind

ICML 2025 Normalizing Flows Are Capable Generative Models Shuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran, David Berthelot, Jiatao Gu, Huangjie Zheng, Tianrong Chen, Miguel Ángel Bautista, Navdeep Jaitly, Joshua M. Susskind

NeurIPSW 2024 Classifier-Free Guidance Is a Predictor-Corrector Arwen Bradley, Preetum Nakkiran

NeurIPS 2024 How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua Susskind

ICLR 2024 LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin

ICLR 2024 Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing Jaroslaw Blasiok, Preetum Nakkiran

ICLR 2024 Vanishing Gradients in Reinforcement Finetuning of Language Models Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin

ICLR 2024 What Algorithms Can Transformers Learn? a Study in Length Generalization Hattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Joshua M. Susskind, Samy Bengio, Preetum Nakkiran

NeurIPS 2024 When Is Multicalibration Post-Processing Necessary? Dutch Hansen, Siddartha Devic, Preetum Nakkiran, Vatsal Sharan

ICLR 2023 Deconstructing Distributions: A Pointwise Framework of Learning Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran

TMLR 2023 Empirical Limitations of the NTK for Understanding Scaling Laws in Deep Learning Nikhil Vyas, Yamini Bansal, Preetum Nakkiran

NeurIPSW 2023 What Algorithms Can Transformers Learn? a Study in Length Generalization Hattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Joshua Susskind, Samy Bengio, Preetum Nakkiran

NeurIPS 2023 When Does Optimizing a Proper Loss Yield Calibration? Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran

NeurIPSW 2022 APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations Elan Rosenfeld, Preetum Nakkiran, Hadi Pouransari, Oncel Tuzel, Fartash Faghri

NeurIPS 2022 Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting Neil Mallinar, James Simon, Amirhesam Abedsoltan, Parthe Pandit, Misha Belkin, Preetum Nakkiran

NeurIPS 2022 Knowledge Distillation: Bad Models Can Be Good Role Models Gal Kaplun, Eran Malach, Preetum Nakkiran, Shai Shalev-Shwartz

NeurIPS 2022 What You See Is What You Get: Principled Deep Learning via Distributional Generalization Bogdan Kulynych, Yao-Yuan Yang, Yaodong Yu, Jarosław Błasiok, Preetum Nakkiran

NeurIPSW 2022 What You See Is What You Get: Principled Deep Learning via Distributional Generalization Bogdan Kulynych, Yao-Yuan Yang, Yaodong Yu, Jaroslaw Blasiok, Preetum Nakkiran

ICLR 2021 Optimal Regularization Can Mitigate Double Descent Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma

NeurIPS 2021 Revisiting Model Stitching to Compare Neural Representations Yamini Bansal, Preetum Nakkiran, Boaz Barak

ICLR 2021 The Deep Bootstrap Framework: Good Online Learners Are Good Offline Generalizers Preetum Nakkiran, Behnam Neyshabur, Hanie Sedghi

ICLR 2020 Deep Double Descent: Where Bigger Models and More Data Hurt Preetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, Ilya Sutskever

Distill 2019 A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' Logan Engstrom, Justin Gilmer, Gabriel Goh, Dan Hendrycks, Andrew Ilyas, Aleksander Madry, Reiichiro Nakano, Preetum Nakkiran, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, Eric Wallace

COLT 2019 Computational Limitations in Robust Classification and Win-Win Results Akshay Degwekar, Preetum Nakkiran, Vinod Vaikuntanathan

NeurIPS 2019 SGD on Neural Networks Learns Functions of Increasing Complexity Dimitris Kalimeris, Gal Kaplun, Preetum Nakkiran, Benjamin Edelman, Tristan Yang, Boaz Barak, Haofeng Zhang