6th Symposium on
Advances in Approximate Bayesian Inference

Sunday, 21 July 2024
Getreidemarkt 9, 1060 Vienna, BA Gebäude, 11th floor (TU the Sky room)
Co-located with ICML

List of papers

Proceedings Track

Accepted papers are available at OpenReview.

  1. Talk +
  2. Implicitly Bayesian Prediction Rules in Deep Learning
    Bruno Kacper Mlodozeniec, Richard E. Turner, David Krueger
  3. Talk +
  4. PAC-Bayesian Soft Actor-Critic Learning
    Bahareh Tasdighi, Abdullah Akgül, Manuel Haussmann, Kenny Kazimirzak Brink, Melih Kandemir
  5. Talk +
  6. Bayesian Optimization for Precision Agriculture with Scalable Probabilistic Models
    Ruhana Azam, Sang T. Truong, samuel bonfim fernandes, Andrew D.B. Leakey, Alexander Lipka, Mohammed El-Kebir, Sanmi Koyejo
  7. Talk +
  8. In-Context In-Context Learning with Transformer Neural Processes
    Matthew Ashman, Cristiana Diaconu, Adrian Weller, Richard E. Turner
  9. Talk +
  10. Fluctuation without dissipation: Microcanonical Langevin Monte Carlo
    Jakob Robnik, Uros Seljak
  11. Talk +
  12. Non-asymptotic approximations of Gaussian neural networks via second-order Poincaré inequalities
    Alberto Bordino, Stefano Favaro, Sandra Fortini

Workshop Track

Accepted papers are available at OpenReview for archival purposes. This does not constitute a proceedings for the symposium.

  1. Poster
  2. Estimating Expectations without Sampling: Neural Stein Estimation
    Mohsin Hasan, Dinghuai Zhang, Cheikh Ahmed, Awa Khouna, Yoshua Bengio
  3. Poster
  4. Gaussian Stochastic Weight Averaging for Bayesian Low-rank Adaptation of Large Language Models
    Emre Onal, Klemens Flöge, Emma Caldwell, Arsen Sheverdin, Vincent Fortuin
  5. Poster
  6. Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood
    Rayen Dhahri, Alexander Immer, Bertrand Charpentier, Stephan Günnemann, Vincent Fortuin
  7. Poster
  8. Can a Confident Prior Replace a Cold Posterior?
    Martin Marek, Brooks Paige, Pavel Izmailov
  9. Poster
  10. Globally Convergent Variational Inference
    Declan McNamara, Jackson Loper, Jeffrey Regier
  11. Poster
  12. Uncertainty-Guided Optimization on Large Language Model Search Trees
    Julia Grosse, Ruotian Wu, Ahmad Rashid, Philipp Hennig, Pascal Poupart, Agustinus Kristiadi
  13. Poster
  14. On Uncertainty Quantification for Near-Bayes Optimal Algorithms
    Ziyu Wang, Christopher C. Holmes
  15. Poster
  16. Warm Start Marginal Likelihood Optimisation for Iterative Gaussian Processes
    Jihao Andreas Lin, Shreyas Padhy, Bruno Kacper Mlodozeniec, José Miguel Hernández-Lobato
  17. Poster
  18. Word Embedding Uncertainty Estimation
    Väinö Yrjänäinen, Isac Boström, Måns Magnusson
  19. Poster
  20. Evaluating approximate Bayesian inference for radio galaxy classification
    Devina Mohan, Anna M M Scaife
  21. Poster
  22. Hamilton Monte Carlo with discrete categorical parameters using the Concrete distribution
    Jakob Torgander, Måns Magnusson, Jonas Wallin
  23. Poster
  24. HybridBNN: Joint Training of Deterministic and Stochastic Layers in Bayesian Neural Nets
    Amin Nejatbakhsh, Julien Boussard
  25. Poster
  26. Explainable Attribution using Additive Gaussian Processes
    Xiaoyu Lu, Alexis Boukouvalas, James Hensman
  27. Poster
  28. Unity by Diversity: Improved Representation Learning in Multimodal VAEs
    Thomas M. Sutter, Yang Meng, Norbert Fortin, Julia E Vogt, Babak Shahbaba, Stephan Mandt
  29. Poster
  30. Ai-sampler: Adversarial Learning of Markov kernels with involutive maps
    Evgenii Egorov, Riccardo Valperga, Stratis Gavves
  31. Poster
  32. Structured Partial Stochasticity in Bayesian Neural Networks
    Tommy Rochussen
  33. Poster
  34. How Useful is Intermittent, Asynchronous Expert Feedback for Bayesian Optimization?
    Agustinus Kristiadi, Felix Strieth-Kalthoff, Sriram Ganapathi Subramanian, Vincent Fortuin, Pascal Poupart, Geoff Pleiss
  35. Poster
  36. On the Properties and Estimation of Pointwise Mutual Information Profiles
    Paweł Czyż, Frederic Grabowski, Julia E Vogt, Niko Beerenwinkel, Alexander Marx
  37. Poster
  38. Variational Linearized Laplace Approximation for Bayesian Deep Learning
    Luis A. Ortega, Simon Rodriguez Santana, Daniel Hernández-Lobato
  39. Poster
  40. Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
    Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Fast Track

  1. Poster
  2. Hodge-Compositional Edge Gaussian Processes
    Maosheng Yang, Viacheslav Borovitskiy, Elvin Isufi
  3. Poster
  4. Transport meets Variational Inference: Controlled Monte Carlo Diffusions
    Francisco Vargas, Shreyas Padhy, Denis Blessing, Nikolas Nüsken
  5. Poster
  6. Stochastic Gradient Descent for Gaussian Processes Done Right
    Jihao Andreas Lin, Shreyas Padhy, Javier Antoran, Austin Tripp, Alexander Terenin, Csaba Szepesvari, José Miguel Hernández-Lobato, David Janz
  7. Poster
  8. The Allocore Tensor Decomposition for Sparse Count Data
    John Hood, Aaron Schein
  9. Poster
  10. Bayesian Semi-structured Subspace Inference
    Daniel Dold, David Ruegamer, Beate Sick, Oliver Dürr
  11. Poster
  12. Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
    Mikkel Jordahn, Pablo Olmos
  13. Poster
  14. Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
    Johannes Zenn, Robert Bamler
  15. Poster
  16. Debiased Distribution Compression
    Lingxiao Li, Raaz Dwivedi, Lester Mackey
  17. Poster
  18. Variational Resampling
    Oskar Kviman, Nicola Branchini, Víctor Elvira, Jens Lagergren
  19. Poster
  20. ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
    Nikita Durasov, Nik Dorndorf, Hieu Le, Pascal Fua
  21. Poster
  22. Batch and match: black-box variational inference with a score-based divergence
    Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
  23. Poster
  24. Adaptive importance sampling for heavy-tailed distributions via alpha-divergence minimization
    Thomas Guilmeau, Nicola Branchini, Emilie Chouzenoux, Víctor Elvira
  25. Poster
  26. How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regression
    Lucas Kook, Chris Kolb, Philipp Schiele, Daniel Dold, Marcel Arpogaus, Cornelius Fritz, Philipp Baumann, Philipp Kopper, Tobias Pielok, Emilio Dorigatti, David Rügamer
  27. Poster
  28. An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation
    Jonas Arruda, Yannik Schälte, Clemens Peiter, Olga Teplytska, Ulrich Jaehde, Jan Hasenauer
  29. Poster
  30. Liouville Flow Importance Sampler
    Yifeng Tian, Nishant Panda, Yen Ting Lin
  31. Poster
  32. Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
    Emanuel Sommer, Lisa Wimmer, Theodore Papamarkou, Ludwig Bothmann, Bernd Bischl, David Rügamer
  33. Poster
  34. Outlier-robust Kalman Filtering through Generalised Bayes
    Gerardo Duran-Martin, Matias Altamirano, Alexander Y. Shestopaloff, Leandro Sánchez-Betancourt, Jeremias Knoblauch, Matt Jones, François-Xavier Briol, Kevin Murphy
  35. Poster
  36. Using Autodiff to Estimate Posterior Moments, Marginals and Samples
    Sam Bowyer, Thomas Heap, Laurence Aitchison
  37. Poster
  38. Partially Stochastic Infinitely Deep Bayesian Neural Networks
    Sergio Calvo-Ordoñez, Matthieu Meunier, Francesco Piatti, Yuantao Shi
  39. Poster
  40. Robust and Conjugate Gaussian Process Regression
    Matias Altamirano Francois-Xavier Briol, Jeremias Knoblauch
  41. Poster
  42. Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
    Fabian Falck*, Ziyu Wang*, Chris Holmes
  43. Poster
  44. Approximate Bayesian Computation with Path Signatures
    Joel Dyer, Patrick Cannon, Sebastian M. Schmon
  45. Poster
  46. IBIA: An Incremental Build-Infer-Approximate Framework for Approximate Inference of Partition Function
    Shivani Bathla, Vinita Vasudevan
  47. Poster
  48. Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
    Marvin Schmitt, Desi R. Ivanova, Daniel Habermann, Ullrich Köthe, Paul-Christian Bürkner, Stefan T. Radev
  49. Poster
  50. Are you using test log-likelihood correctly?
    Sameer K. Deshpande, Soumya Ghosh, Tin D. Nguyen, Tamara Broderick
  51. Poster
  52. Minimizing f-Divergences by Interpolating Velocity Fields
    Song Liu, Jiahao Yu, Jack Simons, Mingxuan Yi, Mark Beaumont
  53. Poster
  54. Function-space Parameterization of Neural Networks for Sequential Learning
    Aidan Scannell, Riccardo Mereu, Paul Edmund Chang, Ella Tamir, Joni Pajarinen, Arno Solin
  55. Poster
  56. Causal Discovery using Bayesian Model Selection
    Anish Dhir, Samuel Power, Mark van der Wilk