Christoph H. Lampert

About Christoph H. Lampert

Christoph H. Lampert, With an exceptional h-index of 49 and a recent h-index of 33 (since 2020), a distinguished researcher at Institute of Science and Technology Austria, specializes in the field of Trustworthy Machine Learning, Lifelong Machine Learning, Transfer Learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Deep neural collapse is provably optimal for the deep unconstrained features model

More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

ELSA: Partial Weight Freezing for Overhead-Free Sparse Network Deployment

1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness

Continual learning: Applications and the road forward

1-Lipschitz Neural Networks are more expressive with N-Activations

PeFLL: Personalized Federated Learning by Learning to Learn

Christoph H. Lampert Information

University

Position

Professor at

Citations(all)

18630

Citations(since 2020)

11207

Cited By

11357

hIndex(all)

49

hIndex(since 2020)

33

i10Index(all)

89

i10Index(since 2020)

67

Email

University Profile Page

Google Scholar

Christoph H. Lampert Skills & Research Interests

Trustworthy Machine Learning

Lifelong Machine Learning

Transfer Learning

Top articles of Christoph H. Lampert

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

arXiv preprint arXiv:2403.06833

2024/3/11

Deep neural collapse is provably optimal for the deep unconstrained features model

Advances in Neural Information Processing Systems

2024/2/13

More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

arXiv preprint arXiv:2402.04054

2024/2/6

ELSA: Partial Weight Freezing for Overhead-Free Sparse Network Deployment

arXiv preprint arXiv:2312.06872

2023/12/11

1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness

arXiv preprint arXiv:2311.16833

2023/11/28

1-Lipschitz Neural Networks are more expressive with N-Activations

arXiv preprint arXiv:2311.06103

2023/11/10

PeFLL: Personalized Federated Learning by Learning to Learn

2023/10/13

Cross-client Label Propagation for Transductive and Semi-Supervised Federated Learning

Transactions on Machine Learning Research

2023/6/7

FedProp: Cross-client Label Propagation for Federated Semi-supervised Learning

arXiv preprint arXiv:2210.06434

2022/10/12

FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data

2022/12/22

Generalization In Multi-Objective Machine Learning

arXiv preprint arXiv:2208.13499

2022/8/29

On the Implementation of Baselines and Lightweight Conditional Model Extrapolation (LIMES) Under Class-Prior Shift

2022/8/21

Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift

2022/8/21

Cram: A compression-aware minimizer

arXiv preprint arXiv:2207.14200

2022/7/28

On the Impossibility of Fairness-Aware Learning from Corrupted Data

2022/3/1

Fairness-aware PAC learning from corrupted data

Journal of Machine Learning Research

2022

Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks

2022

Overcoming Rare-Language Discrimination in Multi-Lingual Sentiment Analysis

2021/12/15

SSSE: Efficiently Erasing Samples from Trained Machine Learning Models

arXiv preprint arXiv:2107.03860

2021/7/8

See List of Professors in Christoph H. Lampert University(Institute of Science and Technology Austria)

Co-Authors

academic-engine