17 citations · 17 across the 14 of their papers we have counts for
16 papers
Adaptive Sampling and Clipping for Private Worst-Case Group Optimization
Max Cairney-Leeming, Amartya Sanyal, Christoph H. Lampert
A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they should work comparably well for ind…
Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control
Fabian Kresse, Christoph H. Lampert
Controlling autonomous systems under real-world conditions often requires policies that can be evaluated with low latency and minimal energy consumption. Unfortunately, these condi…
Learning Quantized Continuous Controllers for Integer Hardware
Fabian Kresse, Christoph H. Lampert
Deploying continuous-control reinforcement learning policies on embedded hardware requires meeting tight latency and power budgets. Small FPGAs can deliver these, but only if costl…
Scalable Interconnect Learning in Boolean Networks
Fabian Kresse, Emily Yu, Christoph H. Lampert
Learned Differentiable Boolean Logic Networks (DBNs) already deliver efficient inference on resource-constrained hardware. We extend them with a trainable, differentiable interconn…
Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
Hossein Zakerinia, Jonathan Scott, Christoph H. Lampert
Personalized federated learning has emerged as a popular approach to training on devices holding statistically heterogeneous data, known as clients. However, most existing approach…
Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
Peter Súkeník, Christoph H. Lampert, Marco Mondelli
The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spur…
Logic Gate Neural Networks are Good for Verification
Fabian Kresse, Emily Yu, Christoph H. Lampert +1
Learning-based systems are increasingly deployed across various domains, yet the complexity of traditional neural networks poses significant challenges for formal verification. Unl…
Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes
Hossein Zakerinia, Christoph H. Lampert
We present new fast-rate PAC-Bayesian generalization bounds for multi-task and meta-learning in the unbalanced setting, i.e. when the tasks have training sets of different sizes, a…
ASIDE: Architectural Separation of Instructions and Data in Language Models
Egor Zverev, Evgenii Kortukov, Alexander Panfilov +5
Despite their remarkable performance, large language models lack elementary safety features, making them susceptible to numerous malicious attacks. In particular, previous work has…
From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning
Hossein Zakerinia, Dorsa Ghobadi, Christoph H. Lampert
Deep learning methods are known to generalize well from training to future data, even in an overparametrized regime, where they could easily overfit. One explanation for this pheno…
Intriguing Properties of Robust Classification
Bernd Prach, Christoph H. Lampert
Despite extensive research since the community learned about adversarial examples 10 years ago, we still do not know how to train high-accuracy classifiers that are guaranteed to b…
DP-KAN: Differentially Private Kolmogorov-Arnold Networks
Nikita P. Kalinin, Simone Bombari, Hossein Zakerinia +1
We study the Kolmogorov-Arnold Network (KAN), recently proposed as an alternative to the classical Multilayer Perceptron (MLP), in the application for differentially private model…
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
Egor Zverev, Sahar Abdelnabi, Soroush Tabesh +2
Instruction-tuned Large Language Models (LLMs) show impressive results in numerous practical applications, but they lack essential safety features that are common in other areas of…
More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms
Hossein Zakerinia, Amin Behjati, Christoph H. Lampert
We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory. Its main advantage over previous work is that it allows for more flexibility in how the t…
1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness
Bernd Prach, Fabio Brau, Giorgio Buttazzo +1
The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical syste…
Continual Learning: Applications and the Road Forward
Eli Verwimp, Rahaf Aljundi, Shai Ben-David +17
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting wh…