Preprints

2026

1. Preprint

   Split Conformal Interval Length under Huber Contamination

   Xiao Zhang, Bowen Zhang, and Lie He^†

   Preprint, 2026

   arXiv

Conference & journal papers

2026

1. NeurIPS

   Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization

   Yunzhen Yao^*, Hongye Wang^*, Yahong Wang, Michael C. Gastpar, Bo Jiang^†, and Lie He^†

   In Advances in Neural Information Processing Systems, 2026

   arXiv
2. ICLR

   Non-Asymptotic Analysis of Efficiency in Conformalized Regression

   Yunzhen Yao, Lie He^†, and Michael Gastpar

   In International Conference on Learning Representations, 2026

   arXiv PDF

2025

1. ICML

   Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective

   Yunzhen Yao, Lie He, and Michael Gastpar

   In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025

   Abs arXiv

   This paper considers the sample-efficiency of preference learning, which models and predicts human choices based on comparative judgments. The minimax optimal estimation error rate Θ(d/n) in classical estimation theory requires that the number of samples n scales linearly with the dimensionality of the feature space d. However, the high dimensionality of the feature space and the high cost of collecting human-annotated data challenge the efficiency of traditional estimation methods. To remedy this, we leverage sparsity in the preference model and establish sharp error rates. We show that under the sparse random utility model, where the parameter of the reward function is k-sparse, the minimax optimal rate can be reduced to Θ(k/n \log(d/k)). Furthermore, we analyze the \ell_1-regularized estimator and show that it achieves a near-optimal rate under mild assumptions on the Gram matrix. Experiments on synthetic data and LLM alignment data validate our theoretical findings, showing that sparsity-aware methods significantly reduce sample complexity and improve prediction accuracy.

2024

1. NeurIPS

   CoBo: Collaborative Learning via Bilevel Optimization

   Diba Hashemi, Lie He^†, and Martin Jaggi

   In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, 2024

2023

1. TMLR

   Provably Personalized and Robust Federated Learning

   Mariel A. Werner, Lie He, Michael I. Jordan, Martin Jaggi, and Sai Praneeth Karimireddy

   Trans. Mach. Learn. Res., 2023
2. NeurIPS

   Debiasing Conditional Stochastic Optimization

   Lie He and Shiva Prasad Kasiviswanathan

   In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023

2022

1. ICLR

   Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing

   Sai Praneeth Karimireddy^*, Lie He^*, and Martin Jaggi

   In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022, 2022

2021

1. FTML

   Advances and Open Problems in Federated Learning

   Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, and 53 more authors

   Found. Trends Mach. Learn., 2021

   DOI
2. ICML

   Learning from History for Byzantine Robust Optimization

   Sai Praneeth Karimireddy, Lie He, and Martin Jaggi

   In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, 2021
3. NeurIPS

   RelaySum for Decentralized Deep Learning on Heterogeneous Data

   Thijs Vogels^*, Lie He^*, Anastasia Koloskova, Sai Praneeth Karimireddy, Tao Lin, Sebastian U. Stich, and 1 more author

   In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, 2021

2018

1. NeurIPS

   COLA: Decentralized Linear Learning

   Lie He^*, An Bian^*, and Martin Jaggi

   In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, 2018

Workshop & technical reports

2022

1. Byzantine-Robust Decentralized Learning via Self-Centered Clipping

   Lie He, Sai Praneeth Karimireddy, and Martin Jaggi

   CoRR, 2022

2020

1. NeurIPS-Workshop

   Secure Byzantine-Robust Machine Learning

   Lie He, Sai Praneeth Karimireddy, and Martin Jaggi

   CoRR, 2020