Nikolay Malkin

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

Gabriel Missael Barco

Adam Coogan

Laurence Perreault-Levasseur

Yashar Hezaveh

2025-11-23

ArXiv (prépublication)

Laurence Perreault-Levasseur

Pixellated Posterior Sampling of Point Spread Functions in Astronomical Images

Gabriel Missael Barco

Yashar Hezaveh

We introduce a novel framework for upsampled Point Spread Function (PSF) modeling using pixel-level Bayesian inference. Accurate PSF charact… (voir plus)erization is critical for precision measurements in many fields including: weak lensing, astrometry, and photometry. Our method defines the posterior distribution of the pixelized PSF model through the combination of an analytic Gaussian likelihood and a highly expressive generative diffusion model prior, trained on a library of HST ePSF templates. Compared to traditional methods (parametric Moffat, ePSF template-based, and regularized likelihood), we demonstrate that our PSF models achieve orders of magnitude higher likelihood and residuals consistent with noise, all while remaining visually realistic. Further, the method applies even for faint and heavily masked point sources, merely producing a broader posterior. By recovering a realistic, pixel-level posterior distribution, our technique enables the first meaningful propagation of detailed PSF morphological uncertainty in downstream analysis. An implementation of our posterior sampling procedure is available on GitHub.

2025-11-23

ArXiv (prépublication)

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (voir plus) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-29

ArXiv (prépublication)

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

Bilun Sun

A major bottleneck in scientific discovery consists of narrowing an exponentially large set of objects, such as proteins or molecules, to a … (voir plus)small set of promising candidates with desirable properties. While this process can rely on expert knowledge, recent methods leverage reinforcement learning (RL) guided by a proxy reward function to enable this filtering. By employing various forms of entropy regularization, these methods aim to learn samplers that generate diverse candidates that are highly rated by the proxy function. In this work, we make two main contributions. First, we show that these methods are liable to generate overly diverse, suboptimal candidates in large search spaces. To address this issue, we introduce a novel unified operator that combines several regularized RL operators into a general framework that better targets peakier sampling distributions. Secondly, we offer a novel, robust RL perspective of this filtering process. The regularization can be interpreted as robustness to a compositional form of uncertainty in the proxy function (i.e., the true evaluation of a candidate differs from the proxy's evaluation). Our analysis leads us to a novel, easy-to-use algorithm we name trajectory general mellowmax (TGM): we show it identifies higher quality, diverse candidates than baselines in both synthetic and real-world tasks. Code: https://github.com/marcojira/tgm.

2025-05-31

arXiv (publié)

Can a Bayesian Oracle Prevent Harm from an Agent?

Michael K. Cohen

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the … (voir plus)long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. Such a risk evaluation would need to be performed at run-time to provide a guardrail against dangerous actions of an AI. Noting that different plausible hypotheses about the world could produce very different outcomes, and because we do not know which one is right, we derive bounds on the safety violation probability predicted under the true but unknown hypothesis. Such bounds could be used to reject potentially dangerous actions. Our main results involve searching for cautious but plausible hypotheses, obtained by a maximization that involves Bayesian posteriors over hypotheses. We consider two forms of this result, in the iid case and in the non-iid case, and conclude with open problems towards turning such theoretical results into practical AI guardrails.

2025-05-06

Conference on Uncertainty in Artificial Intelligence (poster)

proceedings.mlr.press

Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models

Any well-behaved generative model over a variable …

2025-04-30

International Conference on Machine Learning (poster)

Laurence Perreault-Levasseur

proceedings.mlr.press

Solving Bayesian Inverse Problems with Diffusion Priors and Off-Policy RL

Glen Berseth

This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (R… (voir plus)L) objective that can asymptotically solve Bayesian inverse problems optimally. We extend the original work by using RTB to train conditional diffusion model posteriors from pretrained unconditional priors for challenging linear and non-linear inverse problems in vision, and science. We use the objective alongside techniques such as off-policy backtracking exploration to improve training. Importantly, our results show that existing training-free diffusion posterior methods struggle to perform effective posterior inference in latent space due to inherent biases.

2025-03-05

ICLR.cc/2025/Workshop/DeLTa (poster)

Learning Decision Trees as Amortized Structure Inference

Mohammed Mahfoud

Ghait Boukachab

Michał Koziarski

Alex Hernandez-Garcia

Stefan Bauer

2025-03-04

ICLR.cc/2025/Workshop/FPI (poster)

In-Context Parametric Inference: Point or Distribution Estimators?

Bayesian and frequentist inference are two fundamental paradigms in statistical estimation. Bayesian methods treat hypotheses as random vari… (voir plus)ables, incorporating priors and updating beliefs via Bayes' theorem, whereas frequentist methods assume fixed but unknown hypotheses, relying on estimators like maximum likelihood. While extensive research has compared these approaches, the frequentist paradigm of obtaining point estimates has become predominant in deep learning, as Bayesian inference is challenging due to the computational complexity and the approximation gap of posterior estimation methods. However, a good understanding of trade-offs between the two approaches is lacking in the regime of amortized estimators, where in-context learners are trained to estimate either point values via maximum likelihood or maximum a posteriori estimation, or full posteriors using normalizing flows, score-based diffusion samplers, or diagonal Gaussian approximations, conditioned on observations. To help resolve this, we conduct a rigorous comparative analysis spanning diverse problem settings, from linear models to shallow neural networks, with a robust evaluation framework assessing both in-distribution and out-of-distribution generalization on tractable tasks. Our experiments indicate that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems, and we further discuss why this might be the case.

2025-02-16

ArXiv (prépublication)

Action Abstractions for Amortized Sampling

Lena Nehale Ezzine

As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignm… (voir plus)ent and exploration become more challenging, and the long planning horizon hinders mode discovery and generalization. The challenge is particularly pronounced in entropy-seeking RL methods, such as generative flow networks, where the agent must learn to sample from a structured distribution and discover multiple high-reward states, each of which take many steps to reach. To tackle this challenge, we propose an approach to incorporate the discovery of action abstractions, or high-level actions, into the policy optimization process. Our approach involves iteratively extracting action subsequences commonly used across many high-reward trajectories and `chunking' them into a single action that is added to the action space. In empirical evaluation on synthetic and real-world environments, our approach demonstrates improved sample efficiency performance in discovering diverse high-reward objects, especially on harder exploration problems. We also observe that the abstracted high-order actions are interpretable, capturing the latent structure of the reward landscape of the action space. This work provides a cognitively motivated approach to action abstraction in RL and is the first demonstration of hierarchical planning in amortized sequential sampling.

2025-01-21

ICLR.cc/2025/Conference (poster)

Adaptive Teachers for Amortized Samplers

Sungsoo Ahn

Jinkyoo Park

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (voir plus)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \teacher) to guide the training of the primary amortized sampler (the \student). The \teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.

2025-01-21

ICLR.cc/2025/Conference (poster)