arXiv subjects

Shuchin Aeron

Publications and source records attributed to Shuchin Aeron.

At least 19 recordsLinked to original sources

arXiv2026

Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration

A document modeled as a discrete sequence of tokens can be thought of as being generated from a composition of texts from different domains; a README file, for example, moves between prose, code, and configuration. When such a document is corrupted and only frozen domain experts are available, restoring it requires deciding both what is missing and which expert to trust at each position, at test time and without region labels or a trained router. We introduce evidence-aligned local composition, which infers a soft, position-wise weighting over the experts from the marginal evidence of the corrupted observation under a given corruption model, estimating the evidence from the experts' own denoising losses and smoothing the weights across positions. Because the weighting is soft, it recovers a mixture when the true composition is mixed and concentrates on one expert when that suffices. Across a categorical simulator, byte-level experts, and experts fine-tuned from a $1.3$B discrete flow-matching model, the inferred weights track the true regions at $0.85$ field accuracy on naturally mixed scientific documents, and at $0.98$ on constructed mixtures whose regions are lexically disjoint. Restoration improves over a single global weight when the experts are genuinely distinct and reduces to it when they converge, tracking a measure of expert separation.

cs.AI↗

arXiv2026

Measuring Cognitive Engagement in Collaborative Discourse with an Extended ICAP Framework: Comparing Human Annotation, In-Context Learning, and Reflective LLM Agents

Collaboration supports learning and problem-solving, but its effectiveness depends on cognitive engagement during discourse. This study applies an extended 7-point ICAP framework based on the Interactive, Constructive, Active, and Passive modes to characterize variation in cognitive engagement during collaborative dialogue. Engagement was coded by trained human annotators and compared with large language model (LLM)-based labeling approaches, including in-context learning (ICL), zero-shot prompting, and self-reflective agents. Interrater reliability among human annotators was robust across framework refinement stages (kappa = 0.906-0.998), higher than the moderate agreement observed for ICL-based annotation (kappa = 0.541-0.609). The human-refined framework improved agreement among human annotators (Delta kappa = 0.10), but produced only modest gains for ICL-based LLMs (Delta kappa less than 0.04). Agent-refined frameworks improved cross-model agreement but remained below the human-refined framework. These findings highlight the promise of agent-based approaches and the importance of continued interaction between theory-guided human annotation and LLM-based methods in future work.

cs.HC↗

arXiv2026

Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets

In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imbalanced. When classes are balanced and the representation dimension is greater than the number of classes, it is well-known that the optimal representations exhibit Neural Collapse (NC), i.e., representations from the same class collapse to their class means and the class means form an Equiangular Tight Frame (ETF). For imbalanced classes and a large, generalized family of CL losses, we prove that the optimal representations of all samples from the same class collapse to their class means and their geometry exhibits an angular symmetry structure that is determined by the relative class proportions. In general, we show that the geometry can be determined by solving a convex optimization problem. Exploiting this symmetry structure, we analytically investigate a special case where class imbalance is extreme and prove that CL exhibits a phenomenon called Minority Collapse (MC) where all samples from the minority classes (classes with small probabilities) collapse into a single vector, whenever the class imbalance exceeds a threshold, which in turn depends on the regularity properties of the CL loss used and on the number of negative samples. Numerical results are provided to illustrate these phenomena and corroborate the theoretical results. We conclude by identifying a number of open problems.

cs.LG↗

arXiv2026

Building an AI-native Research Ecosystem for Experimental Particle Physics: A Community Vision

Experimental particle physics seeks to understand the universe by probing its fundamental particles and forces and exploring how they govern the large-scale processes that shape cosmic evolution. This whitepaper presents a vision for how Artificial Intelligence (AI) can accelerate discovery in this field. We outline grand challenges that must be addressed to enable transformative breakthroughs and describe how current and planned experimental facilities can implement this vision to advance our understanding of the vast and complex physical world from the smallest to the largest scales. We show how facilities currently under construction, such as the HL-LHC, DUNE and soon EIC, can both benefit from and serve as proving grounds for this vision, while also enabling a longer-term goal for how future experiments -- like FCC-ee at CERN, IceCube-Gen2, a Muon Collider in the U.S., and smaller to mid-scale projects -- can be fully AI-native. We describe how a truly national-scale collaboration, jointly managed across large funding partners, and involving both DOE laboratories and universities, can make this happen.

hep-ex↗

arXiv2026

The Ensemble Inverse Problem: Applications and Methods

We introduce a new multivariate statistical problem that we refer to as the Ensemble Inverse Problem (EIP). The aim of EIP is to invert for an ensemble that is distributed according to the pushforward of a prior under a forward process. In high energy physics (HEP), this is related to a widely known problem called unfolding, which aims to reconstruct the true physics distribution of quantities, such as momentum and angle, from measurements that are distorted by detector effects. In recent applications, the EIP also arises in full waveform inversion (FWI) and inverse imaging with unknown priors. We propose non-iterative inference-time methods that construct posterior samplers based on a new class of conditional generative models, which we call ensemble inverse generative models. For the posterior modeling, these models additionally use the ensemble information contained in the observation set on top of single measurements. Unlike existing methods, our proposed methods avoid explicit and iterative use of the forward model at inference time via training across several sets of truth-observation pairs that are consistent with the same forward model, but originate from a wide range of priors. We demonstrate that this training procedure implicitly encodes the likelihood model. The use of ensemble information helps posterior inference and enables generalization to unseen priors. We benchmark the proposed method on several synthetic and real datasets in inverse imaging, HEP, and FWI. The codes are available at https://github.com/ZhengyanHuan/The-Ensemble-Inverse-Problem--Applications-and-Methods.

cs.LG↗

arXiv2025

Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing empirical success, the theoretical understanding of flow matching remains limited, particularly in terms of sample complexity results. In this work, we provide the first analysis of the sample complexity for flow-matching based generative models without assuming access to the empirical risk minimizer (ERM) of the loss function for estimating the velocity field. Under standard assumptions on the loss function for velocity field estimation and boundedness of the data distribution, we show that a sufficiently expressive neural network can learn a velocity field such that with $\mathcal{O}(\epsilon^{-4})$ samples, such that the Wasserstein-2 distance between the learned and the true distribution is less than $\mathcal{O}(\epsilon)$. The key technical idea is to decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field. Each of these terms are then handled via techniques that may be of independent interest.

cs.LG↗

arXiv2025

From Words to Wisdom: Discourse Annotation and Baseline Models for Student Dialogue Understanding

Identifying discourse features in student conversations is quite important for educational researchers to recognize the curricular and pedagogical variables that cause students to engage in constructing knowledge rather than merely completing tasks. The manual analysis of student conversations to identify these discourse features is time-consuming and labor-intensive, which limits the scale and scope of studies. Leveraging natural language processing (NLP) techniques can facilitate the automatic detection of these discourse features, offering educational researchers scalable and data-driven insights. However, existing studies in NLP that focus on discourse in dialogue rarely address educational data. In this work, we address this gap by introducing an annotated educational dialogue dataset of student conversations featuring knowledge construction and task production discourse. We also establish baseline models for automatically predicting these discourse properties for each turn of talk within conversations, using pre-trained large language models GPT-3.5 and Llama-3.1. Experimental results indicate that these state-of-the-art models perform suboptimally on this task, indicating the potential for future research.

cs.CL↗

arXiv2025

Constraint-Aware Flow Matching via Randomized Exploration

We consider the problem of designing constraint-aware flow matching (FM) models that address the issue of constraint violations commonly observed in vanilla generative models. We consider two scenarios, viz.: (a) when a differentiable distance function to the constraint set is given, and (b) when the constraint set is only available via queries to a membership oracle. For case (a), we propose a simple adaptation of the FM objective with an additional term that penalizes the distance between the constraint set and the generated samples. For case (b), we propose to employ randomization and learn a mean flow that is numerically shown to have a high likelihood of satisfying the constraints. This approach deviates significantly from existing works that require simple convex constraints, knowledge of a barrier function, or a reflection mechanism to constrain the probability flow. Furthermore, in the proposed setting we show that a two-stage approach, where both stages approximate the same original flow but with only the second stage probing the constraints via randomization, is more computationally efficient than the corresponding one-stage approach. Through several synthetic cases of constrained generation, we numerically show that the proposed approaches achieve significant gains in terms of constraint satisfaction while matching the target distributions. As a showcase for a practical oracle-based constraint, we show how our approach can be used for training an adversarial example generator, using queries to a hard-label black-box classifier. We conclude with several future research directions. Our code is available at https://github.com/ZhengyanHuan/FM-RE.

cs.LG↗

arXiv2025

Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications

We propose the linear barycentric coding model (LBCM) which utilizes the linear optimal transport (LOT) metric for analysis and synthesis of probability measures. We provide a closed-form solution to the variational problem characterizing the probability measures in the LBCM and establish equivalence of the LBCM to the set of 2-Wasserstein barycenters in the special case of compatible measures. Computational methods for synthesizing and analyzing measures in the LBCM are developed with finite sample guarantees. One of our main theoretical contributions is to identify an LBCM, expressed in terms of a simple family, which is sufficient to express all probability measures on the closed unit interval. We show that a natural analogous construction of an LBCM in 2 dimensions fails, and we leave it as an open problem to identify the proper extension in more than 1 dimension. We conclude by demonstrating the utility of LBCM for covariance estimation and data imputation.

stat.ML↗

arXiv2025

Synthesis and Analysis of Data as Probability Measures with Entropy-Regularized Optimal Transport

We consider synthesis and analysis of probability measures using the entropy-regularized Wasserstein-2 cost and its unbiased version, the Sinkhorn divergence. The synthesis problem consists of computing the barycenter, with respect to these costs, of reference measures given a set of coefficients belonging to the simplex. The analysis problem consists of finding the coefficients for the closest barycenter in the Wasserstein-2 distance to a given measure. Under the weakest assumptions on the measures thus far in the literature, we compute the derivative of the entropy-regularized Wasserstein-2 cost. We leverage this to establish a characterization of barycenters with respect to the entropy-regularized Wasserstein-2 cost as solutions that correspond to a fixed point of an average of the entropy-regularized displacement maps. This characterization yields a finite-dimensional, convex, quadratic program for solving the analysis problem when the measure being analyzed is a barycenter with respect to the entropy-regularized Wasserstein-2 cost. We show that these coefficients, as well as the value of the barycenter functional, can be estimated from samples with dimension-independent rates of convergence, and that barycentric coefficients are stable with respect to perturbations in the Wasserstein-2 metric. We employ the barycentric coefficients as features for classification of corrupted point cloud data, and show that compared to neural network baselines, our approach is more efficient in small training data regimes.

stat.ML↗

arXiv2024

Alternating minimization algorithm with initialization analysis for r-local and k-sparse unlabeled sensing

Unlabeled sensing is a linear inverse problem with permuted measurements. We propose an alternating minimization (AltMin) algorithm with a suitable initialization for two widely considered permutation models: partially shuffled/$k$-sparse permutations and $r$-local/block diagonal permutations. Key to the performance of the AltMin algorithm is the initialization. For the exact unlabeled sensing problem, assuming either a Gaussian measurement matrix or a sub-Gaussian signal, we bound the initialization error in terms of the number of blocks $s$ and the number of shuffles $k$. Experimental results show that our algorithm is fast, applicable to both permutation models, and robust to choice of measurement matrix. We also test our algorithm on several real datasets for the linked linear regression problem and show superior performance compared to baseline methods.

eess.SP↗

arXiv2024

Towards Universal Unfolding of Detector Effects in High-Energy Physics using Denoising Diffusion Probabilistic Models

Correcting for detector effects in experimental data, particularly through unfolding, is critical for enabling precision measurements in high-energy physics. However, traditional unfolding methods face challenges in scalability, flexibility, and dependence on simulations. We introduce a novel approach to multidimensional object-wise unfolding using conditional Denoising Diffusion Probabilistic Models (cDDPM). Our method utilizes the cDDPM for a non-iterative, flexible posterior sampling approach, incorporating distribution moments as conditioning information, which exhibits a strong inductive bias that allows it to generalize to unseen physics processes without explicitly assuming the underlying distribution. Our results highlight the potential of this method as a step towards a "universal" unfolding tool that reduces dependence on truth-level assumptions, while enabling the unfolding of a wide range of measured distributions with improved adaptability and accuracy.

physics.data-an↗

arXiv2024

Score-based Diffusion Models for Generating Liquid Argon Time Projection Chamber Images

For the first time, we show high-fidelity generation of LArTPC-like data using a generative neural network. This demonstrates that methods developed for natural images do transfer to LArTPC-produced images, which, in contrast to natural images, are globally sparse but locally dense. We present the score-based diffusion method employed. We evaluate the fidelity of the generated images using several quality metrics, including modified measures used to evaluate natural images, comparisons between high-dimensional distributions, and comparisons relevant to LArTPC experiments.

hep-ex↗

arXiv2024

Systematic comparison of semi-supervised and self-supervised learning for medical image classification

In typical medical image classification problems, labeled data is scarce while unlabeled data is more available. Semi-supervised learning and self-supervised learning are two different research directions that can improve accuracy by learning from extra unlabeled data. Recent methods from both directions have reported significant gains on traditional benchmarks. Yet past benchmarks do not focus on medical tasks and rarely compare self- and semi- methods together on an equal footing. Furthermore, past benchmarks often handle hyperparameter tuning suboptimally. First, they may not tune hyperparameters at all, leading to underfitting. Second, when tuning does occur, it often unrealistically uses a labeled validation set that is much larger than the training set. Therefore currently published rankings might not always corroborate with their practical utility This study contributes a systematic evaluation of self- and semi- methods with a unified experimental protocol intended to guide a practitioner with scarce overall labeled data and a limited compute budget. We answer two key questions: Can hyperparameter tuning be effective with realistic-sized validation sets? If so, when all methods are tuned well, which self- or semi-supervised methods achieve the best accuracy? Our study compares 13 representative semi- and self-supervised methods to strong labeled-set-only baselines on 4 medical datasets. From 20000+ GPU hours of computation, we provide valuable best practices to resource-constrained practitioners: hyperparameter tuning is effective, and the semi-supervised method known as MixMatch delivers the most reliable gains across 4 datasets.

cs.CV↗

arXiv2023

Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation Learning

We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning. We propose and analyze a novel min-max framework that seeks a representation which minimizes the maximum (worst-case) generalized contrastive learning loss over all couplings (joint distributions between positive and negative samples subject to marginal constraints) and prove that the resulting min-max optimum representation will be degenerate. This provides the first theoretical justification for incorporating additional regularization constraints on the couplings. We re-interpret the min-max problem through the lens of Optimal Transport (OT) theory and utilize regularized transport couplings to control the degree of hardness of negative examples. Through experiments we demonstrate that the negative samples generated from our designed negative distribution are more similar to the anchor than those generated from the baseline negative distribution. We also demonstrate that entropic regularization yields negative sampling distributions with parametric form similar to that in a recent state-of-the-art negative sampling design and has similar performance in multiple datasets. Utilizing the uncovered connection with OT, we propose a new ground cost for designing the negative distribution and show improved performance of the learned representation on downstream tasks compared to the representation learned when using squared Euclidean cost.

cs.LG↗

arXiv2023

Estimation of entropy-regularized optimal transport maps between non-compactly supported measures

This paper addresses the problem of estimating entropy-regularized optimal transport (EOT) maps with squared-Euclidean cost between source and target measures that are subGaussian. In the case that the target measure is compactly supported or strongly log-concave, we show that for a recently proposed in-sample estimator, the expected squared $L^2$-error decays at least as fast as $O(n^{-1/3})$ where $n$ is the sample size. For the general subGaussian case we show that the expected $L^1$-error decays at least as fast as $O(n^{-1/6})$, and in both cases we have polynomial dependence on the regularization parameter. While these results are suboptimal compared to known results in the case of compactness of both the source and target measures (squared $L^2$-error converging at a rate $O(n^{-1})$) and for when the source is subGaussian while the target is compactly supported (squared $L^2$-error converging at a rate $O(n^{-1/2})$), their importance lie in eliminating the compact support requirements. The proof technique makes use of a bias-variance decomposition where the variance is controlled using standard concentration of measure results and the bias is handled by T1-transport inequalities along with sample complexity results in estimation of EOT cost under subGaussian assumptions. Our experimental results point to a looseness in controlling the variance terms and we conclude by posing several open problems.

stat.ML↗

arXiv2023

Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse

For a widely-studied data model and general loss and sample-hardening functions we prove that the losses of Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised Contrastive Learning (UCL) are minimized by representations that exhibit Neural-Collapse (NC), i.e., the class means form an Equiangular Tight Frame (ETF) and data from the same class are mapped to the same representation. We also prove that for any representation mapping, the HSCL and Hard-UCL (HUCL) losses are lower bounded by the corresponding SCL and UCL losses. In contrast to existing literature, our theoretical results for SCL do not require class-conditional independence of augmented views and work for a general loss function class that includes the widely used InfoNCE loss function. Moreover, our proofs are simpler, compact, and transparent. Similar to existing literature, our theoretical claims also hold for the practical scenario where batching is used for optimization. We empirically demonstrate, for the first time, that Adam optimization (with batching) of HSCL and HUCL losses with random initialization and suitable hardness levels can indeed converge to the NC-geometry if we incorporate unit-ball or unit-sphere feature normalization. Without incorporating hard-negatives or feature normalization, however, the representations learned via Adam suffer from Dimensional-Collapse (DC) and fail to attain the NC-geometry. These results exemplify the role of hard-negative sampling in contrastive representation learning and we conclude with several open theoretical problems for future work. The code can be found at https://github.com/rjiang03/HCL/tree/main

cs.LG↗

arXiv2023

Nonparametric and Regularized Dynamical Wasserstein Barycenters for Sequential Observations

We consider probabilistic models for sequential observations which exhibit gradual transitions among a finite number of states. We are particularly motivated by applications such as human activity analysis where observed accelerometer time series contains segments representing distinct activities, which we call pure states, as well as periods characterized by continuous transition among these pure states. To capture this transitory behavior, the dynamical Wasserstein barycenter (DWB) model of Cheng et al. in 2021 [1] associates with each pure state a data-generating distribution and models the continuous transitions among these states as a Wasserstein barycenter of these distributions with dynamically evolving weights. Focusing on the univariate case where Wasserstein distances and barycenters can be computed in closed form, we extend [1] specifically relaxing the parameterization of the pure states as Gaussian distributions. We highlight issues related to the uniqueness in identifying the model parameters as well as uncertainties induced when estimating a dynamically evolving distribution from a limited number of samples. To ameliorate non-uniqueness, we introduce regularization that imposes temporal smoothness on the dynamics of the barycentric weights. A quantile-based approximation of the pure state distributions yields a finite dimensional estimation problem which we numerically solve using cyclic descent alternating between updates to the pure-state quantile functions and the barycentric weights. We demonstrate the utility of the proposed algorithm in segmenting both simulated and real world human activity time series.

cs.LG↗