34 citations · 150 across the 65 of their papers we have counts for
68 papers
How to Approximate Inference with Subtractive Mixture Models
Lena Zellinger, Nicola Branchini, Lennert De Smet +3
Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance sampling (IS). Recently, mix…
Likelihood Hacking in Probabilistic Program Synthesis
Jacek Karwowski, Younesse Kaddar, Zihuiwen Ye +2
When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likelihood reward by producing program…
Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spaces
Arran Carter, Sanghyeok Choi, Kirill Tamogashev +2
Sampling from a distribution known up to a normalising constant is an important and challenging problem in statistics. Recent years have seen the…
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
Vedant Shah, Johan Obando-Ceron, Vineet Jain +10
The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL objective for LLM training involve…
Lightweight Latent Reasoning for Narrative Tasks
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata
Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a que…
Mind the Information Gap: Unveiling Detailed Morphologies of z 0.5-1.0 Galaxies with SLACS Strong Lenses and Data-Driven Analysis
Ronan Legin, Connor Stone, Alexandre Adam +5
We present new state-of-the-art lens models for strong gravitational lensing systems from the Sloan Lens ACS (SLACS) survey, developed within a Bayesian framework that employs high…
Pixellated Posterior Sampling of Point Spread Functions in Astronomical Images
Connor Stone, Ronan Legin, Alexandre Adam +4
We introduce a novel framework for upsampled Point Spread Function (PSF) modeling using pixel-level Bayesian inference. Accurate PSF characterization is critical for precision meas…
Forgetting is Everywhere
Ben Sanati, Thomas L. Lee, Trevor McInroe +4
A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principle…
Reinforced sequential Monte Carlo for amortised sampling
Sanghyeok Choi, Sarthak Mittal, Víctor Elvira +2
This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state a connection between seque…
Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Oskar Kviman, Kirill Tamogashev, Nicola Branchini +3
Learning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applications. When no ground-truth trajec…
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal +9
Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference to make a prediction. Inference-time co…
Data-to-Energy Stochastic Dynamics
Kirill Tamogashev, Esmeralda S. Whitammer
The Schrödinger bridge problem is concerned with finding a stochastic dynamical system bridging two marginal distributions that minimises a certain transportation cost. This proble…
Adaptive Destruction Processes for Diffusion Samplers
Timofei Gritsaev, Nikita Morozov, Kirill Tamogashev +5
This paper explores the challenges and benefits of a trainable destruction process in diffusion samplers -- diffusion-based generative models trained to sample an unnormalised dens…
Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning
Marco Jiralerspong, Esther Derman, Danilo Vucetic +5
A major bottleneck in scientific discovery consists of narrowing an exponentially large set of objects, such as proteins or molecules, to a small set of promising candidates with d…
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
Magdalena Proszewska, Nikolay Malkin, N. Siddharth
Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. The…
Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings
Andreas Sochopoulos, Nikolay Malkin, Nikolaos Tsagkas +3
Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. Ho…
Solving Bayesian inverse problems with diffusion priors and off-policy RL
Luca Scimeca, Siddarth Venkatraman, Moksh Jain +14
This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (RL) objective that can asymptotically sol…
Learning Decision Trees as Amortized Structure Inference
Mohammed Mahfoud, Ghait Boukachab, Michał Koziarski +4
Building predictive models for tabular data presents fundamental challenges, notably in scaling consistently, i.e., more resources translating to better performance, and generalizi…
In-Context Parametric Inference: Point or Distribution Estimators?
Sarthak Mittal, Yoshua Bengio, Nikolay Malkin +1
Bayesian and frequentist inference are two fundamental paradigms in statistical estimation. Bayesian methods treat hypotheses as random variables, incorporating priors and updating…
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Siddarth Venkatraman, Mohsin Hasan, Minsu Kim +5
Any well-behaved generative model over a variable can be expressed as a deterministic transformation of an exogenous ('outsourced') Gaussian noise variable $\mathbf{z}…
From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
Julius Berner, Lorenz Richter, Marcin Sendera +2
We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing m…
Mixtures of In-Context Learners
Giwon Hong, Emile van Krieken, Edoardo Ponti +2
In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratica…
Proof Flow: Preliminary Study on Generative Flow Network Language Model Tuning for Formal Reasoning
Matthew Ho, Vincent Zhu, Xiaoyin Chen +3
Reasoning is a fundamental substrate for solving novel and complex problems. Deliberate efforts in learning and developing frameworks around System 2 reasoning have made great stri…
Action abstractions for amortized sampling
Oussama Boussif, Léna Néhale Ezzine, Joseph D Viviano +6
As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignment and exploration become more challeng…