Peter Sorrenson

5 papers · 2020–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 📈 Trend Setter

Venues

ICLR (2) AISTATS (1) ICML (1) NeurIPS (1)

Top co-authors

Felix Draxler (3) Armand Rousselot (3) Ullrich Köthe (3) Ullrich Koethe (2) Lea Zimmermann (2) Sander Hummerich (2) Christoph Schnoerr (1) Carsten Rother (1) Daniel Behrend-Uriarte (1)

Research topics

Deep Learning (5) Machine Learning (5) Core Methods (5) Models (5) Optimization & Theory (2) Mathematics & Optimization (1) Bayesian & Probabilistic (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Optimization (1) Probability (1)

Keywords

normalizing flow (4) maximum likelihood (3) generative model (3) neural network (2) latent variable (1) molecule generation (1) flow-based model (1) data manifold (1) change of variable (1) nonlinear ica (1) maximum likelihood training (1) score model (1) free-form flow (1) injective flow (1) fermat distance (1) bottleneck architecture (1) high dimension (1) geodesics (1) representation learning (1) density-based distances (1)

Papers

Learning Distances from Data with Normalizing Flows and Score Matching ICML 2025 Free-form Flows: Make Any Architecture a Normalizing Flow AISTATS 2024 Learning Distributions on Manifolds with Free-Form Flows NeurIPS 2024 Lifting Architectural Constraints of Injective Flows ICLR 2024 Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN) ICLR 2020