Justin Domke - RankMe

90 papers A* 26A 11Misc 1Journal 43Unranked 8

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI. AISTATS Abhinav Agrawal, Justin Domke
2025	J	`jnl`	Large Language Bayes. CoRR Justin Domke
2025	J	`jnl`	Model Informed Flows for Bayesian Inference of Probabilistic Programs. CoRR Joohwan Ko, Justin Domke
2025	A*	`conf`	Understanding the difficulties of posterior predictive estimation. ICML Abhinav Agrawal, Justin Domke
2024	J	`jnl`	Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI. CoRR Abhinav Agrawal, Justin Domke
2024	A*	`conf`	Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models. NeurIPS Jinlin Lai, Justin Domke, Daniel R. Sheldon
2024	J	`jnl`	Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models. CoRR Jinlin Lai, Daniel Sheldon, Justin Domke
2024	A	`conf`	Joint control variate for faster black-box variational inference. AISTATS Xi Wang, Tomas Geffner, Justin Domke
2024	A	`conf`	Sample Average Approximation for Black-Box Variational Inference. UAI Javier Burroni, Justin Domke, Daniel Sheldon
2024	A	`conf`	Simulation-Based Stacking. AISTATS Yuling Yao, Bruno Régaldo-Saint Blancard, Justin Domke
2024	J	`jnl`	Understanding and mitigating difficulties in posterior predictive evaluation. CoRR Abhinav Agrawal, Justin Domke
2023	A*	`conf`	Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier. NeurIPS Yuling Yao, Justin Domke
2023	J	`jnl`	Discriminative calibration. CoRR Yuling Yao, Justin Domke
2023	A	`conf`	Langevin Diffusion Variational Inference. AISTATS Tomas Geffner, Justin Domke
2023	A*	`conf`	Provable convergence guarantees for black-box variational inference. NeurIPS Justin Domke, Robert M. Gower, Guillaume Garrigos
2023	J	`jnl`	Provable convergence guarantees for black-box variational inference. CoRR Justin Domke, Guillaume Garrigos, Robert M. Gower
2023	J	`jnl`	Sample Average Approximation for Black-Box VI. CoRR Javier Burroni, Justin Domke, Daniel Sheldon
2023	J	`jnl`	Simulation based stacking. CoRR Yuling Yao, Bruno Régaldo-Saint Blancard, Justin Domke
2023	J	`jnl`	U-Statistics for Importance-Weighted Variational Inference. CoRR Javier Burroni, Kenta Takatsu, Justin Domke, Daniel Sheldon
2023	J	`jnl`	U-Statistics for Importance-Weighted Variational Inference. Trans. Mach. Learn. Res. Javier Burroni, Kenta Takatsu, Justin Domke, Daniel Sheldon
2022	J	`jnl`	A Dual Control Variate for doubly stochastic optimization and black-box variational inference. CoRR Xi Wang, Tomas Geffner, Justin Domke
2022	J	`jnl`	Arbitrary conditional inference in variational autoencoders via fast prior network training. Mach. Learn. Ga Wu, Justin Domke, Scott Sanner
2022	J	`jnl`	Langevin Diffusion Variational Inference. CoRR Tomas Geffner, Justin Domke
2022	A*	`conf`	Variational Inference with Locally Enhanced Bounds for Hierarchical Models. ICML Tomas Geffner, Justin Domke
2022	J	`jnl`	Variational Inference with Locally Enhanced Bounds for Hierarchical Models. CoRR Tomas Geffner, Justin Domke
2022	A	`conf`	Variational Marginal Particle Filters. AISTATS Jinlin Lai, Justin Domke, Daniel Sheldon
2021	A*	`conf`	Amortized Variational Inference for Simple Hierarchical Models. NeurIPS Abhinav Agrawal, Justin Domke
2021	J	`jnl`	Amortized Variational Inference for Simple Hierarchical Models. CoRR Abhinav Agrawal, Justin Domke
2021	J	`jnl`	An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulations. CoRR Justin Domke
2021	J	`jnl`	Empirical Evaluation of Biased Methods for Alpha Divergence Minimization. CoRR Tomas Geffner, Justin Domke
2021	A*	`conf`	MCMC Variational Inference via Uncorrected Hamiltonian Annealing. NeurIPS Tomas Geffner, Justin Domke
2021	J	`jnl`	MCMC Variational Inference via Uncorrected Hamiltonian Annealing. CoRR Tomas Geffner, Justin Domke
2021	A*	`conf`	On the difficulty of unbiased alpha divergence minimization. ICML Tomas Geffner, Justin Domke
2021	J	`jnl`	Variational Marginal Particle Filters. CoRR Jinlin Lai, Daniel Sheldon, Justin Domke
2020	A	`conf`	A Rule for Gradient Estimator Selection, with an Application to Variational Inference. AISTATS Tomas Geffner, Justin Domke
2020	A*	`conf`	Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization. NeurIPS Abhinav Agrawal, Daniel Sheldon, Justin Domke
2020	J	`jnl`	Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization. CoRR Abhinav Agrawal, Daniel Sheldon, Justin Domke
2020	A*	`conf`	Approximation Based Variance Reduction for Reparameterization Gradients. NeurIPS Tomas Geffner, Justin Domke
2020	J	`jnl`	Approximation Based Variance Reduction for Reparameterization Gradients. CoRR Tomas Geffner, Justin Domke
2020	J	`jnl`	Moment-Matching Conditions for Exponential Families with Conditioning or Hidden Data. CoRR Justin Domke
2020	J	`jnl`	On the Difficulty of Unbiased Alpha Divergence Minimization. CoRR Tomas Geffner, Justin Domke
2020	A*	`conf`	Provable Smoothness Guarantees for Black-Box Variational Inference. ICML Justin Domke
2019	J	`jnl`	A Rule for Gradient Estimator Selection, with an Application to Variational Inference. CoRR Tomas Geffner, Justin Domke
2019	A*	`conf`	Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation. NeurIPS Justin Domke, Daniel Sheldon
2019	J	`jnl`	Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation. CoRR Justin Domke, Daniel Sheldon
2019	A*	`conf`	Provable Gradient Variance Guarantees for Black-Box Variational Inference. NeurIPS Justin Domke
2019	J	`jnl`	Provable Gradient Variance Guarantees for Black-Box Variational Inference. CoRR Justin Domke
2019	J	`jnl`	Provable Smoothness Guarantees for Black-Box Variational Inference. CoRR Justin Domke
2019	A*	`conf`	Thompson Sampling and Approximate Inference. NeurIPS My Phan, Yasin Abbasi-Yadkori, Justin Domke
2019	J	`jnl`	Thompson Sampling and Approximate Inference. CoRR My Phan, Yasin Abbasi-Yadkori, Justin Domke
2018	J	`jnl`	Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding. CoRR Ga Wu, Justin Domke, Scott Sanner
2018	A*	`conf`	Importance Weighting and Variational Inference. NeurIPS Justin Domke, Daniel Sheldon
2018	J	`jnl`	Importance Weighting and Variational Inference. CoRR Justin Domke, Daniel Sheldon
2018	A*	`conf`	Sparse Covariance Modeling in High Dimensions with Gaussian Processes. NeurIPS Rui Li, Kishan KC, Feng Cui, Justin Domke, Anne R. Haake
2018	A*	`conf`	Using Large Ensembles of Control Variates for Variational Inference. NeurIPS Tomas Geffner, Justin Domke
2018	J	`jnl`	Using Large Ensembles of Control Variates for Variational Inference. CoRR Tomas Geffner, Justin Domke
2017	A*	`conf`	A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI. ICML Justin Domke
2017	J	`jnl`	A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI. CoRR Justin Domke
2016	A	`conf`	Clamping Improves TRW and Mean Field Approximations. AISTATS Adrian Weller, Justin Domke
2015	J	`jnl`	Clamping Improves TRW and Mean Field Approximations. CoRR Adrian Weller, Justin Domke
2015	A*	`conf`	Loss-Calibrated Monte Carlo Action Selection. AAAI Ehsan Abbasnejad, Justin Domke, Scott Sanner
2015	—	`conf`	Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets. NIPS Justin Domke
2015	J	`jnl`	Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets. CoRR Justin Domke
2015	—	`conf`	Reflection, Refraction, and Hamiltonian Monte Carlo. NIPS Hadi Mohasel Afshar, Justin Domke
2014	J	`jnl`	Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems. CoRR Aaron J. Defazio, Tibério S. Caetano, Justin Domke
2014	A*	`conf`	Finito: A faster, permutable incremental gradient method for big data problems. ICML Aaron Defazio, Justin Domke, Tibério S. Caetano
2014	J	`jnl`	Projecting Ising Model Parameters for Fast Mixing. CoRR Justin Domke, Xianghang Liu
2014	—	`conf`	Projecting Markov Random Field Parameters for Fast Mixing. NIPS Xianghang Liu, Justin Domke
2014	J	`jnl`	Projecting Markov Random Field Parameters for Fast Mixing. CoRR Xianghang Liu, Justin Domke
2014	J	`jnl`	Structured Learning via Logistic Regression. CoRR Justin Domke
2013	J	`jnl`	Learning Graphical Model Parameters with Approximate Marginal Inference CoRR Justin Domke
2013	J	`jnl`	Learning Graphical Model Parameters with Approximate Marginal Inference. IEEE Trans. Pattern Anal. Mach. Intell. Justin Domke
2013	—	`conf`	Projecting Ising Model Parameters for Fast Mixing. NIPS Justin Domke, Xianghang Liu
2013	—	`conf`	Structured Learning via Logistic Regression. NIPS Justin Domke
2012	A	`conf`	Generic Methods for Optimization-Based Modeling. AISTATS Justin Domke
2012	J	`jnl`	Learning Convex Inference of Marginals CoRR Justin Domke
2011	A*	`conf`	Dual Decomposition for Marginal Inference. AAAI Justin Domke
2011	A*	`conf`	Parameter learning with truncated message-passing. CVPR Justin Domke
2010	—	`conf`	Implicit Differentiation by Perturbation. NIPS Justin Domke
2009	J	`jnl`	Image Transformations and Blurring. IEEE Trans. Pattern Anal. Mach. Intell. Justin Domke, Yiannis Aloimonos
2009	—	`—`	Tractable Learning and Inference in High-Treewidth Graphical Models. Justin Domke
2008	A	`conf`	Learning Convex Inference of Marginals. UAI Justin Domke
2008	Misc	`conf`	Measuring 1 ICASSP Konstantinos Bitsakos, Justin Domke, Cornelia Fermüller, Yiannis Aloimonos
2008	A*	`conf`	Who killed the directed model? CVPR Justin Domke, Alap Karapurkar, Yiannis Aloimonos
2007	A*	`conf`	Multiple View Image Reconstruction: A Harmonic Approach. CVPR Justin Domke, Yiannis Aloimonos
2007	A*	`conf`	Signals on Pencils of Lines. ICCV Justin Domke, Yiannis Aloimonos
2006	—	`conf`	A Probabilistic Framework for Correspondence and Egomotion. WDV Justin Domke, Yiannis Aloimonos
2006	—	`conf`	A Probabilistic Notion of Correspondence and the Epipolar Constraint. 3DPVT Justin Domke, Yiannis Aloimonos
2006	A	`conf`	Deformation and Viewpoint Invariant Color Histograms. BMVC Justin Domke, Yiannis Aloimonos
2006	A*	`conf`	Integration of Visual and Inertial Information for Egomotion: a Stochastic Approach. ICRA Justin Domke, Yiannis Aloimonos