arXiv subjects

Thin Nguyen

Publications and source records attributed to Thin Nguyen.

At least 19 recordsLinked to original sources

arXiv2026

Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent

Several geometry-aware approaches to low-rank adaptation have emerged for parameter-efficient fine-tuning of large pre-trained models. These methods aim to take full advantage of the geometric structure of low-rank manifolds for improving the efficiency in subspace utilization and reducing redundancy by enforcing orthogonality constraints during optimization. The strong empirical results of these techniques have motivated further study into whether predictions from such geometry-based adaptation methods could be overconfident. In this paper, we build on the singular value decomposition factorization of adapters to develop a framework based on Stein variational gradient descent (SVGD). In this formulation, the low-rank matrices are transported along the Stiefel manifold to match the targeted distributions while retaining their crucial geometric structure. Since this geometry-aware SVGD approach provides multiple solutions during inference, it supports uncertainty quantification and produces better-calibrated adapters on the Stiefel manifold. Extensive experiments show that our method delivers strong model calibration and attains higher prediction accuracy than SVGD and related uncertainty estimation methods that are formulated in Euclidean space.

cs.LG↗

arXiv2026

Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering

Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-language question answering. However, directly feeding raw numerical series into LLMs suffers from a tokenization bottleneck: Byte Pair Encoding fragments continuous values into unstable tokens whose embeddings lack meaningful metric structure, resulting in the loss of magnitude, scale, and trend information. Prior methods use patch-based encoders that split the series into fixed windows, locking in one granularity that breaks patterns and hides exact timesteps, through a separate module that rarely transfers across datasets with different lengths or sampling rates. To address this challenge, we propose CADE (Contrastive Alignment with Direct Embedding), a novel framework for TSQA built upon two key components: direct timestep embedding and semantic alignment. The proposed framework maps each timestep directly into the LLM embedding space through a point-wise linear encoder and MLP projector, preserving exact index-level access while eliminating the need for patching and padding. To further bridge the semantic gap between time-series and language representations, we introduce a novel one-directional supervised contrastive loss that aligns time-series embeddings with frozen class-name text anchors. Experimental results on the public Time-MQA benchmark demonstrate that our framework consistently improves performance across six TSQA tasks, outperforming both open-source and proprietary LLM baselines.

cs.CL↗

arXiv2026

BSO: Safety Alignment Is Density Ratio Matching

Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement learning, and primal-dual updates. Recent direct preference optimization approaches simplify training but incorporate safety through ad-hoc modifications such as multi-stage procedures or heuristic margin terms, lacking a principled derivation. We show that the likelihood ratio of the optimal safe policy admits a closed-form decomposition that reduces safety alignment to a density ratio matching problem. Minimizing Bregman divergences between the data and model ratios yields Bregman Safety Optimization (BSO), a family of single-stage loss functions, each induced by a convex generator, that provably recover the optimal safe policy. BSO is both general and simple: it requires no auxiliary models, introduces only one hyperparameter beyond standard preference optimization, and recovers existing safety-aware methods as special cases. Experiments across safety alignment benchmarks show that BSO consistently improves the safety-helpfulness trade-off.

cs.LG↗

arXiv2026

Neural Autoregressive Flows for Markov Boundary Learning

Recovering Markov boundary -- the minimal set of variables that maximizes predictive performance for a response variable -- is crucial in many applications. While recent advances improve upon traditional constraint-based techniques by scoring local causal structures, they still rely on nonparametric estimators and heuristic searches, lacking theoretical guarantees for reliability. This paper investigates a framework for efficient Markov boundary discovery by integrating conditional entropy from information theory as a scoring criterion. We design a novel masked autoregressive network to capture complex dependencies. A parallelizable greedy search strategy in polynomial time is proposed, supported by analytical evidence. We also discuss how initializing a graph with learned Markov boundaries accelerates the convergence of causal discovery. Comprehensive evaluations on real-world and synthetic datasets demonstrate the scalability and superior performance of our method in both Markov boundary discovery and causal discovery tasks.

cs.LG↗

arXiv2025

Large Language Models for Imbalanced Classification: Diversity makes the difference

Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minority samples to rebalance the dataset. Most existing methods, such as SMOTE, require converting categorical variables into numerical vectors, which often leads to information loss. Recently, large language model (LLM)-based methods have been introduced to overcome this limitation. However, current LLM-based approaches typically generate minority samples with limited diversity, reducing robustness and generalizability in downstream classification tasks. To address this gap, we propose a novel LLM-based oversampling method designed to enhance diversity. First, we introduce a sampling strategy that conditions synthetic sample generation on both minority labels and features. Second, we develop a new permutation strategy for fine-tuning pre-trained LLMs. Third, we fine-tune the LLM not only on minority samples but also on interpolated samples to further enrich variability. Extensive experiments on 10 tabular datasets demonstrate that our method significantly outperforms eight SOTA baselines. The generated synthetic samples are both realistic and diverse. Moreover, we provide theoretical analysis through an entropy-based perspective, proving that our method encourages diversity in the generated samples.

cs.LG↗

arXiv2025

Universal Multi-Domain Translation via Diffusion Routers

Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen in training, limiting their practicality and excluding many cross-domain mappings. We introduce universal MDT (UMDT), a generalization of MDT that seeks to translate between any pair of $K$ domains using only $K-1$ paired datasets with a central domain. To tackle this problem, we propose Diffusion Router (DR), a unified diffusion-based framework that models all central$\leftrightarrow$non-central translations with a single noise predictor conditioned on the source and target domain labels. DR enables indirect non-central translations by routing through the central domain. We further introduce a novel scalable learning strategy with a variational-bound objective and an efficient Tweedie refinement procedure to support direct non-central mappings. Through evaluation on three large-scale UMDT benchmarks, DR achieves state-of-the-art results for both indirect and direct translations, while lowering sampling cost and unlocking novel tasks such as sketch$\leftrightarrow$segmentation. These results establish DR as a scalable and versatile framework for universal translation across multiple domains.

cs.LG↗

arXiv2025

CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning

Large language model (LLM) agents-especially smaller, open-source models-often produce causally invalid or incoherent actions in collaborative tasks due to their reliance on surface-level correlations rather than grounded causal reasoning. This limitation undermines their performance in terms of coordination and planning in dynamic environments. We address this challenge with CausalPlan, a two-phase framework that integrates explicit structural causal reasoning into the LLM planning process. At the core of CausalPlan is the Structural Causal Action (SCA) model, which learns a causal graph from agent trajectories to capture how prior actions and current environment states influence future decisions. This structure is then used to guide action selection by assigning causal scores to LLM-generated proposals, reweighting them accordingly, or falling back to causally grounded alternatives when needed. By embedding this causal knowledge directly into the decision loop, CausalPlan constrains planning to intervention-consistent behaviours without requiring fine-tuning of the LLM itself. We evaluate CausalPlan on the Overcooked-AI benchmark across five multi-agent coordination tasks and four LLMs of varying sizes: Gemma-7B, Llama-8B, Qwen-14B, and Llama-70B. Experimental results show that CausalPlan consistently reduces invalid actions and improves collaboration in both AI-AI and human-AI settings, outperforming strong reinforcement learning baselines. Our findings highlight the value of causality-driven planning for deploying efficient, interpretable, and generalisable multi-agent LLM systems.

cs.AI↗

arXiv2025

Leveraging Novel Ensemble Learning Techniques and Landsat Multispectral Data for Estimating Olive Yields in Tunisia

Olive production is an important tree crop in Mediterranean climates. However, olive yield varies significantly due to climate change. Accurately estimating yield using remote sensing and machine learning remains a complex challenge. In this study, we developed a streamlined pipeline for olive yield estimation in the Kairouan and Sousse governorates of Tunisia. We extracted features from multispectral reflectance bands, vegetation indices derived from Landsat-8 OLI and Landsat-9 OLI-2 satellite imagery, along with digital elevation model data. These spatial features were combined with ground-based field survey data to form a structured tabular dataset. We then developed an automated ensemble learning framework, implemented using AutoGluon to train and evaluate multiple machine learning models, select optimal combinations through stacking, and generate robust yield predictions using five-fold cross-validation. The results demonstrate strong predictive performance from both sensors, with Landsat-8 OLI achieving R2 = 0.8635 and RMSE = 1.17 tons per ha, and Landsat-9 OLI-2 achieving R2 = 0.8378 and RMSE = 1.32 tons per ha. This study highlights a scalable, cost-effective, and accurate method for olive yield estimation, with potential applicability across diverse agricultural regions globally.

eess.SP↗

arXiv2025

Identifying Causal Direction via Variational Bayesian Compression

Telling apart the cause and effect between two random variables with purely observational data is a challenging problem that finds applications in various scientific disciplines. A key principle utilized in this task is the algorithmic Markov condition, which postulates that the joint distribution, when factorized according to the causal direction, yields a more succinct codelength compared to the anti-causal direction. Previous approaches approximate these codelengths by relying on simple functions or Gaussian processes (GPs) with easily evaluable complexity, compromising between model fitness and computational complexity. To address these limitations, we propose leveraging the variational Bayesian learning of neural networks as an interpretation of the codelengths. This allows the improvement of model fitness, while maintaining the succinctness of the codelengths, and the avoidance of the significant computational complexity of the GP-based approaches. Extensive experiments on both synthetic and real-world benchmarks in cause-effect identification demonstrate the effectiveness of our proposed method, showing promising performance enhancements on several datasets in comparison to most related methods.

cs.LG↗

arXiv2025

Clustering-based Meta Bayesian Optimization with Theoretical Guarantee

Bayesian Optimization (BO) is a well-established method for addressing black-box optimization problems. In many real-world scenarios, optimization often involves multiple functions, emphasizing the importance of leveraging data and learned functions from prior tasks to enhance efficiency in the current task. To expedite convergence to the global optimum, recent studies have introduced meta-learning strategies, collectively referred to as meta-BO, to incorporate knowledge from historical tasks. However, in practical settings, the underlying functions are often heterogeneous, which can adversely affect optimization performance for the current task. Additionally, when the number of historical tasks is large, meta-BO methods face significant scalability challenges. In this work, we propose a scalable and robust meta-BO method designed to address key challenges in heterogeneous and large-scale meta-tasks. Our approach (1) effectively partitions transferred meta-functions into highly homogeneous clusters, (2) learns the geometry-based surrogate prototype that capture the structural patterns within each cluster, and (3) adaptively synthesizes meta-priors during the online phase using statistical distance-based weighting policies. Experimental results on real-world hyperparameter optimization (HPO) tasks, combined with theoretical guarantees, demonstrate the robustness and effectiveness of our method in overcoming these challenges.

cs.LG↗

arXiv2025

h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform

We introduce a theoretical framework for diffusion-based image editing by formulating it as a reverse-time bridge modeling problem. This approach modifies the backward process of a pretrained diffusion model to construct a bridge that converges to an implicit distribution associated with the editing target at time 0. Building on this framework, we propose h-Edit, a novel editing method that utilizes Doob's h-transform and Langevin Monte Carlo to decompose the update of an intermediate edited sample into two components: a "reconstruction" term and an "editing" term. This decomposition provides flexibility, allowing the reconstruction term to be computed via existing inversion techniques and enabling the combination of multiple editing terms to handle complex editing tasks. To our knowledge, h-Edit is the first training-free method capable of performing simultaneous text-guided and reward-model-based editing. Extensive experiments, both quantitative and qualitative, show that h-Edit outperforms state-of-the-art baselines in terms of editing effectiveness and faithfulness. Our source code is available at https://github.com/nktoan/h-edit.

cs.CV↗

arXiv2025

Amortized Conditional Independence Testing

Testing for the conditional independence structure in data is a fundamental and critical task in statistics and machine learning, which finds natural applications in causal discovery - a highly relevant problem to many scientific disciplines. Existing methods seek to design explicit test statistics that quantify the degree of conditional dependence, which is highly challenging yet cannot capture nor utilize prior knowledge in a data-driven manner. In this study, an entirely new approach is introduced, where we instead propose to amortize conditional independence testing and devise ACID - a novel transformer-based neural network architecture that learns to test for conditional independence. ACID can be trained on synthetic data in a supervised learning fashion, and the learned model can then be applied to any dataset of similar natures or adapted to new domains by fine-tuning with a negligible computational cost. Our extensive empirical evaluations on both synthetic and real data reveal that ACID consistently achieves state-of-the-art performance against existing baselines under multiple metrics, and is able to generalize robustly to unseen sample sizes, dimensionalities, as well as non-linearities with a remarkably low inference time.

stat.ML↗

arXiv2025

Bidirectional Diffusion Bridge Models

Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. However, existing methods are limited by their unidirectional nature, requiring separate models for forward and reverse translations. This not only doubles the computational cost but also restricts their practicality. In this work, we introduce the Bidirectional Diffusion Bridge Model (BDBM), a scalable approach that facilitates bidirectional translation between two coupled distributions using a single network. BDBM leverages the Chapman-Kolmogorov Equation for bridges, enabling it to model data distribution shifts across timesteps in both forward and backward directions by exploiting the interchangeability of the initial and target timesteps within this framework. Notably, when the marginal distribution given endpoints is Gaussian, BDBM's transition kernels in both directions possess analytical forms, allowing for efficient learning with a single network. We demonstrate the connection between BDBM and existing bridge methods, such as Doob's h-transform and variational approaches, and highlight its advantages. Extensive experiments on high-resolution I2I translation tasks demonstrate that BDBM not only enables bidirectional translation with minimal additional cost but also outperforms state-of-the-art bridge models. Our source code is available at [https://github.com/kvmduc/BDBM||https://github.com/kvmduc/BDBM].

cs.CV↗

arXiv2025

Causal Discovery via Bayesian Optimization

Existing score-based methods for directed acyclic graph (DAG) learning from observational data struggle to recover the causal graph accurately and sample-efficiently. To overcome this, in this study, we propose DrBO (DAG recovery via Bayesian Optimization)-a novel DAG learning framework leveraging Bayesian optimization (BO) to find high-scoring DAGs. We show that, by sophisticatedly choosing the promising DAGs to explore, we can find higher-scoring ones much more efficiently. To address the scalability issues of conventional BO in DAG learning, we replace Gaussian Processes commonly employed in BO with dropout neural networks, trained in a continual manner, which allows for (i) flexibly modeling the DAG scores without overfitting, (ii) incorporation of uncertainty into the estimated scores, and (iii) scaling with the number of evaluations. As a result, DrBO is computationally efficient and can find the accurate DAG in fewer trials and less time than existing state-of-the-art methods. This is demonstrated through an extensive set of empirical evaluations on many challenging settings with both synthetic and real data. Our implementation is available at https://github.com/baosws/DrBO.

cs.LG↗

arXiv2024

Generating Realistic Tabular Data with Large Language Models

While most generative models show achievements in image data generation, few are developed for tabular data generation. Recently, due to success of large language models (LLM) in diverse tasks, they have also been used for tabular data generation. However, these methods do not capture the correct correlation between the features and the target variable, hindering their applications in downstream predictive tasks. To address this problem, we propose a LLM-based method with three important improvements to correctly capture the ground-truth feature-class correlation in the real data. First, we propose a novel permutation strategy for the input data in the fine-tuning phase. Second, we propose a feature-conditional sampling approach to generate synthetic samples. Finally, we generate the labels by constructing prompts based on the generated samples to query our fine-tuned LLM. Our extensive experiments show that our method significantly outperforms 10 SOTA baselines on 20 datasets in downstream tasks. It also produces highly realistic synthetic samples in terms of quality and diversity. More importantly, classifiers trained with our synthetic data can even compete with classifiers trained with the original data on half of the benchmark datasets, which is a significant achievement in tabular data generation.

cs.LG↗

arXiv2024

Enabling Causal Discovery in Post-Nonlinear Models with Normalizing Flows

Post-nonlinear (PNL) causal models stand out as a versatile and adaptable framework for modeling intricate causal relationships. However, accurately capturing the invertibility constraint required in PNL models remains challenging in existing studies. To address this problem, we introduce CAF-PoNo (Causal discovery via Normalizing Flows for Post-Nonlinear models), harnessing the power of the normalizing flows architecture to enforce the crucial invertibility constraint in PNL models. Through normalizing flows, our method precisely reconstructs the hidden noise, which plays a vital role in cause-effect identification through statistical independence testing. Furthermore, the proposed approach exhibits remarkable extensibility, as it can be seamlessly expanded to facilitate multivariate causal discovery via causal order identification, empowering us to efficiently unravel complex causal relationships. Extensive experimental evaluations on both simulated and real datasets consistently demonstrate that the proposed method outperforms several state-of-the-art approaches in both bivariate and multivariate causal discovery tasks.

cs.LG↗

arXiv2024

Scalable Variational Causal Discovery Unconstrained by Acyclicity

Bayesian causal discovery offers the power to quantify epistemic uncertainties among a broad range of structurally diverse causal theories potentially explaining the data, represented in forms of directed acyclic graphs (DAGs). However, existing methods struggle with efficient DAG sampling due to the complex acyclicity constraint. In this study, we propose a scalable Bayesian approach to effectively learn the posterior distribution over causal graphs given observational data thanks to the ability to generate DAGs without explicitly enforcing acyclicity. Specifically, we introduce a novel differentiable DAG sampling method that can generate a valid acyclic causal graph by mapping an unconstrained distribution of implicit topological orders to a distribution over DAGs. Given this efficient DAG sampling scheme, we are able to model the posterior distribution over causal graphs using a simple variational distribution over a continuous domain, which can be learned via the variational inference framework. Extensive empirical experiments on both simulated and real datasets demonstrate the superior performance of the proposed model compared to several state-of-the-art baselines.

cs.LG↗

arXiv2024

Reinforcement Learning for Causal Discovery without Acyclicity Constraints

Recently, reinforcement learning (RL) has proved a promising alternative for conventional local heuristics in score-based approaches to learning directed acyclic causal graphs (DAGs) from observational data. However, the intricate acyclicity constraint still challenges the efficient exploration of the vast space of DAGs in existing methods. In this study, we introduce ALIAS (reinforced dAg Learning wIthout Acyclicity conStraints), a novel approach to causal discovery powered by the RL machinery. Our method features an efficient policy for generating DAGs in just a single step with an optimal quadratic complexity, fueled by a novel parametrization of DAGs that directly translates a continuous space to the space of all DAGs, bypassing the need for explicitly enforcing acyclicity constraints. This approach enables us to navigate the search space more effectively by utilizing policy gradient methods and established scoring functions. In addition, we provide compelling empirical evidence for the strong performance of ALIAS in comparison with state-of-the-arts in causal discovery over increasingly difficult experiment conditions on both synthetic and real datasets.

cs.LG↗