arXiv subjects

Nghia Bui

Publications and source records attributed to Nghia Bui.

4 recordsLinked to original sources

arXiv2026

GRAIN: Group Aggregation via Min-Norm Objective

Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern deep learning: large models fine-tuned or trained on limited data traverse flat loss landscapes with many nearly-equivalent minima, and stochastic factors (initialization, data order, dropout, hardware non-determinism) can route optimization to very different solutions. The rise of large pretrained models (LPMs) makes the problem more urgent: training cost is high, downstream data is often small, and repeated runs for variance reduction are prohibitive. We introduce \textbf{GRAIN} (\textbf{G}roup \textbf{A}ggregation via m\textbf{IN}-norm objective), a lightweight training algorithm that replaces the mean aggregation used in mini-batch optimization (both across mini-batches and within a mini-batch) with a min-norm convex combination of group-wise gradients. \mName guarantees a non-negative inner product between the aggregated update and every group gradient, resolving intra- and inner-batch gradient conflict, and retains an $\mathcal{O}(1/T)$ convergence rate comparable to SGD. Under mild smoothness and absolute-continuity assumptions, the min-norm solution differs almost surely from the arithmetic mean, which yields a uniform-stability bound for \mName strictly tighter than the standard bound for SGD. Empirically across generation, classification, and regression at LPM scale, \mName delivers consistent improvements in mean performance and reductions in run-to-run variance over a broad suite of tasks, with no extra training-time or storage cost beyond a single backward pass.

cs.LG↗

arXiv2026

Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems

Deep recommender systems (DRS) often face challenges in balancing computational efficiency and model accuracy, especially when handling high-dimensional input features. Existing methods either focus on improving accuracy while neglecting training efficiency or prioritize efficiency at the cost of suboptimal accuracy across tasks. We propose Light-FMP: Lightweight Feature and Model Pruning for Enhanced DRS, a lightweight framework that addresses the challenges through three key phases: \textit{pretraining}, \textit{pruning}, and \textit{continued training}. Using a hard concrete distribution, a masking layer is efficiently pretrained on a small data subset to identify important features. The model and features are then pruned, and training continues on the remaining dataset with domain-adapted parameters. Experiments on benchmark datasets from real-world recommender systems demonstrate that Light-FMP outperforms existing methods in both efficiency and accuracy while maintaining scalability and robustness.

cs.IR↗

arXiv2026

Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model gets stuck, leading to degraded performance and unstable training. One possible reason for this is the cancellation of gradients across training examples. To address this problem, we propose a novel algorithm, dynamic scaled gradient descent (\mName), that directly modifies the gradients returned by training examples, specifically, scaling down the gradients of correctly classified examples using a dynamic scaler. This strategy offers both theoretical and empirical advantages in improving training stability. Experiments on a variety of benchmark datasets, spanning multiple tasks and large pretrained models, demonstrate that our method consistently reduces performance variance and surpasses the accuracy of existing approaches.

cs.LG↗

arXiv2025

Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models

The impact of random seeds in fine-tuning large language models (LLMs) has been largely overlooked despite its potential influence on model performance.In this study, we systematically evaluate the effects of random seeds on LLMs using the GLUE and SuperGLUE benchmarks. We analyze the macro-level impact through traditional metrics like accuracy and F1, calculating their mean and variance to quantify performance fluctuations. To capture the micro-level effects, we introduce a novel metric, consistency, measuring the stability of individual predictions across runs. Our experiments reveal significant variance at both macro and micro levels, underscoring the need for careful consideration of random seeds in fine-tuning and evaluation.

cs.CL↗