91 citations
- Indian Institute of Science BangaloreIN28 papers
- Indian Institute of Technology MadrasIN12 papers
- University of FreiburgDE7 papers
- Carnegie Mellon UniversityUS5 papers
- Robert Bosch (Germany)DE5 papers
- Robert Bosch (United States)US5 papers
- Karlsruhe Institute of TechnologyDE4 papers
- Robert Bosch (Taiwan)TW4 papers
- Technical University of MunichDE4 papers
- University of TübingenDE4 papers
- Intel (United States)US3 papers
- Leibniz University HannoverDE3 papers
5 papers · 2 filters
Convergence Analysis of Homotopy-SGD for non-convex optimization
Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh +2
First-order stochastic methods for solving large-scale non-convex optimization problems are widely used in many big-data applications, e.g. training deep neural networks as well as…
Hyperparameter Transfer Across Developer Adjustments
Danny Stoll, Jörg K. H. Franke, Diane Wagner +2
After developer adjustments to a machine learning (ML) algorithm, how can the results of an old hyperparameter optimization (HPO) automatically be used to speedup a new HPO? This q…
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
Filipe de Avila Belbute-Peres, Thomas D. Economon, J. Zico Kolter
Solving large complex partial differential equations (PDEs), such as those that arise in computational fluid dynamics (CFD), is a computationally expensive process. This has motiva…
ResNet After All? Neural ODEs and Their Numerical Solution
Katharina Ott, Prateek Katiyar, Philipp Hennig +1
A key appeal of the recently proposed Neural Ordinary Differential Equation (ODE) framework is that it seems to provide a continuous-time extension of discrete residual neural netw…
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
Kanil Patel, William Beluch, Bin Yang +2
Post-hoc multi-class calibration is a common approach for providing high-quality confidence estimates of deep neural network predictions. Recent work has shown that widely used sca…