Papers for

data scientists in physics

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Meta learning improves identifiability in hybrid deep generative models

On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution

Abstract: The interest in leveraging physics-based inductive bias in deep learning has resulted in recent development of hybrid deep generative models (hybrid-DGMs) that integrate known physics-based mathematical expressions in neural generative models. To identify these hybrid-DGMs requires inferring parameters of the physics-based component along with their neural component. The identifiability of these hybrid-DGMs, however, has not yet been theoretically probed or established. How does the existing theory of the un-identifiability of general DGMs apply to hybrid-DGMs? What may be an effective approach to construct a hybrid-DGM with theoretically-proven identifiability? This paper provides the first theoretical probe into the identifiability of hybrid-DGMs, and presents meta-learning as a novel solution to construct identifiable hybrid-DGMs. On synthetic and real-data benchmarks, we provide strong empirical evidence for the un-identifiability of existing hybrid-DGMs using unconditional priors, and strong identifiability results of the presented meta-formulations of hybrid-DGMs. Code is available at https://github.com/GoForIt-YYB/Meta-Hybrid-VAE.

Fri 23 OctMachine Learning
The gist
Sometimes, computer programs try to learn how things work by mixing known scientific rules with flexible neural networks. However, it can be hard for these programs to figure out the exact parts of the model that come from science and the parts that come from learning. The authors studied whether these hybrid models can be uniquely identified and found that many existing models cannot. They propose a new way using meta-learning that helps these models figure out the correct parts more reliably, and they tested this on both fake and real data with good results.
Open → 2610.32748v1

Exhaustive dataset improves symbolic regression with less repetition

Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression

Abstract: Neural symbolic regression (SR) models require diverse datasets of mathematical expressions for robust training. However, existing datasets rely predominantly on stochastic sampling methods, which suffer from high structural redundancy and incomplete functional coverage. To address this, we introduce an exhaustive dataset of univariate canonical skeletons generated via a deterministic constrained context-free grammar. A canonical skeleton acts as a generic structural representation that subsumes more specific functional forms, eliminating redundant expressions and avoiding repeated computational efforts. Although our dataset consists of univariate skeletons, it is designed to support the decomposable SR paradigm to solve multivariate SR problems without assuming linear separability. Furthermore, we pair this dataset with a sampling strategy that generates clean numerical data without triggering numerical instabilities or relying on artificial protected operators. Canonicalizing two existing neural SR datasets reveals that our dataset is substantially more compact, eliminates structural repetitions, and achieves a uniform operator distribution free of simplicity bias. Finally, we establish a benchmark of 150 SR problems across three tiers, on which state-of-the-art SR methods are shown to struggle significantly.

Wed 14 OctMachine Learning
The gist
Finding mathematical formulas from data is hard, and training AI models to do this needs lots of varied examples. The authors created a new, carefully built set of basic formula structures that cover all possibilities without repeating similar ones. This helps AI learn better and avoids problems seen in previous datasets. Their method also makes it easier to tackle complicated formulas involving multiple variables by breaking them down. They tested existing AI tools on these new problems and found that they still struggle, suggesting the dataset is a challenging benchmark.
Open → 2610.20108v1

Machine learning slightly improves invisible dark boson detection at collider

Machine Learning for Invisible Dark Boson Searches at the Electron-Ion Collider

Abstract: We investigate whether adding $t$, the positive magnitude of the squared nuclear four-momentum transfer, enables boosted decision trees (BDTs) to improve invisible-dark-boson selection relative to optimized rectangular cuts at the Electron-Ion Collider. We model coherent exclusive scalar and vector production at generator level in electron-gold collisions at 18 GeV by 100 GeV per nucleon. Both methods use identical weighted samples, inputs, preselection, and optimization objectives. Using only electron information, the BDT provided no consistent advantage over optimized cuts for signal selection across 11 masses for each boson type. When both methods also use $t$, the BDT distinguishes signal from background slightly better than optimized cuts at 10 GeV for both boson types. These results motivate further investigation of machine learning in EIC dark-boson searches through exclusive processes where $t$ can be reconstructed.

Fri 18 SeptMachine Learning
The gist
Finding invisible particles called dark bosons is challenging because they leave no direct signals in detectors. The authors studied whether a machine learning method called boosted decision trees (BDTs) can do better than simple threshold cuts at spotting these particles in electron-gold collisions. Using only electron data, the machine learning approach showed no clear improvement. However, when including a specific measured quantity called momentum transfer, BDTs performed slightly better for certain particle masses. This suggests machine learning may offer small benefits in these searches when more detailed data is used.
Open → 2609.22484v1