Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study

• URL: http://arxiv.org/abs/2606.20933v1
• Date: Thu, 18 Jun 2026 20:51:42 GMT
• Title: Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study
• Abstract summary: This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models.<n>We conduct a systematic empirical study of all $3 times 6 = 18$ combinations of six classifiers paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets.<n>Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across
• Score: 48.83701310501069
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The choice of loss function and optimizer is an important decision, that shapes further model training. Yet automated architecture search pipelines (AutoML) benefits significantly more from the optimal pairing selection and vice versa. This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models. We conduct a systematic empirical study of all $3 \times 6 = 18$ combinations of six optimizers (SGD+Momentum, Adam, AdamW, RMSprop, Adagrad, Adadelta), paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets (CelebA-Gender, CIFAR-10, CIFAR-100, ImageNette, MNIST, SVHN). The 18 loss-optimizer configurations are applied to each of the 33 compatible base architectures taken from the LEMUR pool, resulting in 594 variants that were generated fully automatically by a source-level injection pipeline and evaluated under fixed hyperparameters, ensuring that observed accuracy differences are attributable solely to the loss-optimizer pairing. Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across architecture families and datasets. NGL is a competitive alternative to CEL on standard convolutional classifiers, but only when paired with adaptive optimizers; it degrades substantially with SGD or accumulation-based methods. Adagrad and Adadelta consistently underperform under fixed hyperparameters regardless of loss function, highlighting their sensitivity to learning rate tuning. These findings provide actionable guidance for loss-optimizer selection within NNGPT Framework.

Related papers

• A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability [10.86517852984593]
  We present a unified reinforcement-learning framework that discovers compact parametrized quantum circuits (PQCs) for data-scarce device modeling.<n>A graph neural network (GNN) policy searches circuit architectures using leave-one-group-out cross-validation (LOGOCV) error on held-out process or geometry groups as the reward.<n>The framework achieves the lowest mean absolute error (MAE) on all 11 targets versus six classical baselines, with 59% lower error (Ioff) and 81% tighter fold variability (VTH) for HEMTs and 84% lower error (V
  arXiv  Detail & Related papers  (2026-09-04T15:15:40Z)
• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD [91.71050339479261]
  This report presents an end-to-end optimization practice on the Ascend NPU SuperPOD.<n>We develop a hierarchical optimization framework spanning model-level parallelism, computation-communication orchestration, and low-level kernel execution.<n>The resulting system achieves 34.22% Model FLOPs Utilization (MFU) with a 2.93x improvement over the open-source baseline recipe.
  arXiv  Detail & Related papers  (2026-07-22T13:49:17Z)
• MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization [3.7323766833175718]
  MAGE (Memory-Augmented Goal Prompt Evolution) is a controlled analysis framework for studying component interaction in prompt optimization.<n>Our experiments uncover a previously unreported phenomenon, the Prompt Optimization Coupling Effect (POCE), when multiple optimization signals operate within a closed reflective loop.
  arXiv  Detail & Related papers  (2026-07-11T10:05:58Z)
• Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization [8.412194372218895]
  We introduce Singularity-aware Adam (S-Adam), a novel that stabilizes training by dynamically modulating step sizes based on local geometric instability.<n>S-Adam incorporates an adaptive damping mechanism that decelerates updates in high-instability regions while preserving fast convergence in smooth basins.<n> Empirical evaluations on optimal Quantization-Aware Training (QAT) and high-noise small-batch learning demonstrate that S-Adam consistently outperforms AdamW and Prox-SGD.
  arXiv  Detail & Related papers  (2026-05-28T08:00:40Z)
• Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization [76.38917994186733]
  Diff3R is a novel framework that bridges feed-forward prediction and test-time optimization.<n>We show that it can be seamlessly integrated into existing feed-forward 3DGS architectures for both pose-given and pose-free methods.
  arXiv  Detail & Related papers  (2026-04-01T15:40:20Z)
• Efficient Differentiable Causal Discovery via Reliable Super-Structure Learning [51.20606796019663]
  We propose ALVGL, a novel and general enhancement to the differentiable causal discovery pipeline.<n>ALVGL employs a sparse and low-rank decomposition to learn the precision matrix of the data.<n>We show that ALVGL not only achieves state-of-the-art accuracy but also significantly improves optimization efficiency.
  arXiv  Detail & Related papers  (2026-01-09T02:18:59Z)
• One Size Does Not Fit All: Architecture-Aware Adaptive Batch Scheduling with DEBA [9.344832445480415]
  We introduce DEBA, an adaptive batch scheduler that monitors gradient variance, gradient norm variation and loss variation.<n>We demonstrate that the architecture fundamentally determines adaptation efficacy.
  arXiv  Detail & Related papers  (2025-11-05T19:19:39Z)
• FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks [1.663204995903499]
  FORTRESS (Function-composition Optimized Real-Time Resilient Structural) is a new architecture that balances accuracy and speed by using a special method.<n>Fortress incorporates three key innovations: a systematic depthwise separable convolution framework, adaptive TiKAN integration, and multi-scale attention fusion.<n>The architecture achieves remarkable efficiency gains with 91% parameter reduction (31M to 2.9M), 91% computational complexity reduction (13.7 to 1.17 GFLOPs), and 3x inference speed improvement.
  arXiv  Detail & Related papers  (2025-07-16T23:17:58Z)
• Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment [57.03947082589616]
  Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. We study this and find that preference data gives a better learning signal when the underlying responses are contrastive. We introduce Contrastive Learning from AI Revisions (CLAIR), a data-creation method which leads to more contrastive preference pairs. Our best model, trained on 32K CLAIR preferences with APO, improves Llama-3-8B-Instruct by 7.65%, closing the gap with GPT4-turbo by 45%.
  arXiv  Detail & Related papers  (2024-08-12T16:24:51Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices [37.559461866831754]
  We benchmark a variety of loss functions with different algorithmic choices for deep AUROC optimization problem. We highlight the essential choices such as positive sampling rate, regularization, normalization/activation, and weights. Our findings show that although Adam-type method is more competitive from training perspective, but it does not outperform others from testing perspective.
  arXiv  Detail & Related papers  (2022-03-27T00:47:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.