activity
20192023
most citedHyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

157 citations · 317 across the 18 of their papers we have counts for

collaborators
Showing 2021 · cs.LGShow all

5 papers · 2 filters

cs.LG2021★ 10 cited

Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective

Luca Scimeca, Seong Joon Oh, Sanghyuk Chun +2

Deep neural networks (DNNs) often rely on easy-to-learn discriminatory features, or cues, that are not necessarily essential to the problem at hand. For example, ducks in an image…

cs.LG2021★ 3 cited

Continuous-Depth Neural Models for Dynamic Graph Prediction

Michael Poli, Stefano Massaroli, Clayton M. Rabideau +4

We introduce the framework of continuous-depth graph neural networks (GNNs). Neural graph differential equations (Neural GDEs) are formalized as the counterpart to GNNs where the i…

cs.LG2021★ 7 cited

Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions

Michael Poli, Stefano Massaroli, Luca Scimeca +6

Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs…

cs.LG2021★ 1 cited

Differentiable Multiple Shooting Layers

Stefano Massaroli, Michael Poli, Sho Sonoda +4

We detail a novel class of implicit neural models. Leveraging time-parallel methods for differential equations, Multiple Shooting Layers (MSLs) seek solutions of initial value prob…

cs.LG2021

Learning Stochastic Optimal Policies via Gradient Descent

Stefano Massaroli, Michael Poli, Stefano Peluchetti +3

We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of…