Tomas Geffner

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 24

Top Topics

Diffusion Model

Exponential Family

Variational Inference

Hierarchical Model

Top Venues

Publications

Xi Wang, Tomas Geffner, Justin Domke
Joint control variate for faster black-box variational inference. AISTATS (2024)
Siyi Gu, Minkai Xu, Alexander S. Powers, Weili Nie, Tomas Geffner, Karsten Kreis, Jure Leskovec, Arash Vahdat, Stefano Ermon
Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization. CoRR (2024)
Tomas Geffner, Javier Antorán, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Agrin Hilmkil, Joel Jennings, Meyer Scetbon, Miltiadis Allamanis, Cheng Zhang
Deep End-to-end Causal Inference. Trans. Mach. Learn. Res. 2024 (2024)
Tomas Geffner, George Papamakarios, Andriy Mnih
Compositional Score Modeling for Simulation-Based Inference. ICML (2023)
Tomas Geffner, Justin Domke
Langevin Diffusion Variational Inference. AISTATS (2023)
Xi Wang, Tomas Geffner, Justin Domke
A Dual Control Variate for doubly stochastic optimization and black-box variational inference. CoRR (2022)
Tomas Geffner, Justin Domke
Variational Inference with Locally Enhanced Bounds for Hierarchical Models. ICML (2022)
Tomas Geffner, Justin Domke
Variational Inference with Locally Enhanced Bounds for Hierarchical Models. CoRR (2022)
Tomas Geffner, Javier Antoran, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang
Deep End-to-end Causal Inference. CoRR (2022)
Tomas Geffner, George Papamakarios, Andriy Mnih
Score Modeling for Simulation-based Inference. CoRR (2022)
Tomas Geffner, Justin Domke
Langevin Diffusion Variational Inference. CoRR (2022)
Tomas Geffner, Justin Domke
Empirical Evaluation of Biased Methods for Alpha Divergence Minimization. CoRR (2021)
Tomas Geffner, Justin Domke
MCMC Variational Inference via Uncorrected Hamiltonian Annealing. NeurIPS (2021)
Tomas Geffner, Justin Domke
On the difficulty of unbiased alpha divergence minimization. ICML (2021)
Tomas Geffner, Justin Domke
MCMC Variational Inference via Uncorrected Hamiltonian Annealing. CoRR (2021)
Tomas Geffner, Justin Domke
A Rule for Gradient Estimator Selection, with an Application to Variational Inference. AISTATS (2020)
Tomas Geffner, Justin Domke
On the Difficulty of Unbiased Alpha Divergence Minimization. CoRR (2020)
Tomas Geffner, Justin Domke
Approximation Based Variance Reduction for Reparameterization Gradients. CoRR (2020)
Tomas Geffner, Justin Domke
Approximation Based Variance Reduction for Reparameterization Gradients. NeurIPS (2020)
Tomas Geffner, Justin Domke
A Rule for Gradient Estimator Selection, with an Application to Variational Inference. CoRR (2019)
Tomas Geffner, Hector Geffner
Compact Policies for Fully Observable Non-Deterministic Planning as SAT. ICAPS (2018)
Tomas Geffner, Justin Domke
Using Large Ensembles of Control Variates for Variational Inference. NeurIPS (2018)
Tomas Geffner, Justin Domke
Using Large Ensembles of Control Variates for Variational Inference. CoRR (2018)
Tomas Geffner, Hector Geffner
Compact Policies for Fully-Observable Non-Deterministic Planning as SAT. CoRR (2018)
Tomas Geffner, Hector Geffner
Width-Based Planning for General Video-Game Playing. AIIDE (2015)