306 citations · 1.4k across the 39 of their papers we have counts for
39 papers
PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
Hamish Flynn, David Reeb, Melih Kandemir +1
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Ba…
Validation of Composite Systems by Discrepancy Propagation
David Reeb, Kanil Patel, Karim Barsim +2
Assessing the validity of a real-world system with respect to given quality criteria is a common yet costly task in industrial applications due to the vast number of required real-…
Utilizing Expert Features for Contrastive Learning of Time-Series Representations
Manuel Nonnenmacher, Lukas Oldenburg, Ingo Steinwart +1
We present an approach that incorporates expert knowledge for time-series representation learning. Our method employs expert features to replace the commonly used data transformati…
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits
Hamish Flynn, David Reeb, Melih Kandemir +1
We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer infor…
SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
Manuel Nonnenmacher, Thomas Pfeil, Ingo Steinwart +1
Pruning neural networks reduces inference time and memory costs. On standard hardware, these benefits will be especially prominent if coarse-grained structures, like feature maps,…
Which Minimizer Does My Neural Network Converge To?
Manuel Nonnenmacher, David Reeb, Ingo Steinwart
The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error. We explain how common variants of the standard NN training procedu…