7 citations · 23 across the 14 of their papers we have counts for
14 papers
Implicit Regularization of Large Neural Networks via Mean-Field Formulation
Beatrice Acciaio, Jakob Heiss, Gudmund Pammer +1
We propose a mathematical framework to explain implicit regularization from early stopping during the training of overparametrized neural networks. In the mean-field limit, the par…
JUCAL: Jointly Calibrating Aleatoric and Epistemic Uncertainty in Classification Tasks
Jakob Heiss, Sören Lambrecht, Jakob Weissteiner +4
We study post-calibration uncertainty for trained ensembles of classifiers. Specifically, we consider both aleatoric (label noise) and epistemic (model) uncertainty. Among the most…
Revealing the temporal dynamics of antibiotic anomalies in the infant gut microbiome with neural jump ODEs
Anja Adamov, Markus Chardonnet, Florian Krach +3
Detecting anomalies in irregularly sampled multi-variate time-series is challenging, especially in data-scarce settings. Here we introduce an anomaly detection framework for irregu…
CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk
Ilia Azizi, Juraj Bodik, Jakob Heiss +1
Accurate uncertainty quantification is critical for reliable predictive modeling. Existing methods typically address either aleatoric uncertainty due to measurement noise or episte…
Nonparametric Filtering, Estimation and Classification using Neural Jump ODEs
Jakob Heiss, Florian Krach, Thorsten Schmidt +1
Neural Jump ODEs model the conditional expectation between observations by neural ODEs and jump at arrival of new observations. They have demonstrated effectiveness for fully data-…
Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
Ermis Soumalias, Jakob Heiss, Jakob Weissteiner +1
We study the design of iterative combinatorial auctions (ICAs). The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address th…
Machine Learning-Powered Combinatorial Clock Auction
Ermis Soumalias, Jakob Weissteiner, Jakob Heiss +1
We study the design of iterative combinatorial auctions (ICAs). The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address th…
Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework
William Andersson, Jakob Heiss, Florian Krach +1
The Path-Dependent Neural Jump Ordinary Differential Equation (PD-NJ-ODE) is a model for predicting continuous-time stochastic processes with irregular and incomplete observations.…
How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part II: the Multi-D Case of Two Layers with Random First Layer
Jakob Heiss, Josef Teichmann, Hanna Wutte
Randomized neural networks (randomized NNs), where only the terminal layer's weights are optimized constitute a powerful model class to reduce computational time in training the ne…
Bayesian Optimization-based Combinatorial Assignment
Jakob Weissteiner, Jakob Heiss, Julien Siems +1
We study the combinatorial assignment domain, which includes combinatorial auctions and course allocation. The main challenge in this domain is that the bundle space grows exponent…
How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterization
Jakob Heiss, Josef Teichmann, Hanna Wutte
In practice, multi-task learning (through learning features shared among tasks) is an essential property of deep neural networks (NNs). While infinite-width limits of NNs can provi…
Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment
Jakob Weissteiner, Jakob Heiss, Julien Siems +1
Many important resource allocation problems involve the combinatorial assignment of items, e.g., auctions or course allocation. Because the bundle space grows exponentially in the…
NOMU: Neural Optimization-based Model Uncertainty
Jakob Heiss, Jakob Weissteiner, Hanna Wutte +2
We study methods for estimating model uncertainty for neural networks (NNs) in regression. To isolate the effect of model uncertainty, we focus on a noiseless setting with scarce t…
How Implicit Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part I: the 1-D Case of Two Layers with Random First Layer
Jakob Heiss, Josef Teichmann, Hanna Wutte
In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show…