Quiet Feature Learning in Algorithmic Tasks

• URL: http://arxiv.org/abs/2505.03997v2
• Date: Mon, 18 Aug 2025 18:57:07 GMT
• Title: Quiet Feature Learning in Algorithmic Tasks
• Abstract summary: We train Transformer-based language models on ten foundational algorithmic tasks.<n>We observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends.<n>Probing the models' internal representations reveals that quiet features are learned prior to any decrease in task loss.
• Score: 1.9249287163937978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the validation loss barely improves, then abruptly decreases. Probing the models' internal representations reveals that quiet features are learned prior to any decrease in task loss. These quiet features represent intermediate algorithmic computations that do not by themselves improve the output loss. Ablation experiments demonstrate that individual quiet features are causally necessary for task performance. Our results demonstrate that substantial representational progress can remain hidden beneath an apparently flat loss curve, challenging the prevailing use of cross-entropy as a proxy for learning and motivating richer diagnostics for monitoring model training.

Related papers

• Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns [48.062049009807446]
  downstream capabilities such as in-context learning are known to emerge abruptly past a certain model scale.<n>We demonstrate that the emergence of capabilities such as pattern completion and indirect object identification corresponds to the abrupt learning of task-relevant attention patterns.<n>We train transformer models on synthetic linear map and cellular automata datasets, and we show that the difficulty of learning attention patterns depends on context length and pattern sparsity.
  arXiv  Detail & Related papers  (2026-06-23T17:51:10Z)
• Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates [10.06646055401747]
  Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining.<n>Existing methods mitigate this by modifying the fine-tuning objective to suppress high-loss tokens or sequences.<n>We introduce FINCH, a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average while matching the task performance of standard fine-tuning.
  arXiv  Detail & Related papers  (2026-05-19T15:36:52Z)
• On Neural Scaling Laws for Weather Emulation through Continual Training [76.70310203875866]
  We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting.<n>To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture.<n>We show that models trained in this minimalist way follow predictable scaling trends and even outperform standard cosine learning rate schedules.
  arXiv  Detail & Related papers  (2026-03-26T17:37:25Z)
• Provable In-Context Learning of Nonlinear Regression with Transformers [58.018629320233174]
  In-context learning (ICL) is the ability to perform unseen tasks using task-specific prompts without updating parameters.<n>Recent research has actively explored the training dynamics behind ICL.<n>This paper investigates more complex nonlinear regression tasks, aiming to uncover how transformers acquire in-context learning capabilities.
  arXiv  Detail & Related papers  (2025-07-28T00:09:28Z)
• Dynamical loss functions shape landscape topography and improve learning in artificial neural networks [0.9208007322096533]
  We show how to transform cross-entropy and mean squared error into dynamical loss functions. We show how they significantly improve validation accuracy for networks of varying sizes.
  arXiv  Detail & Related papers  (2024-10-14T16:27:03Z)
• Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective [66.80315289020487]
  Warmup-Stable-Decay (WSD) schedule uses a constant learning rate to produce a main branch of iterates that can continue indefinitely without a pre-specified compute budget.<n>We show that pretraining loss exhibits a river valley landscape, which resembles a deep valley with a river at its bottom.<n>Inspired by the theory, we introduce WSD-S, a variant of WSD that reuses previous checkpoints' decay phases and keeps only one main branch.
  arXiv  Detail & Related papers  (2024-10-07T16:49:39Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture. We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• Stepping on the Edge: Curvature Aware Learning Rate Tuners [24.95412499942206]
  Curvature information is the largest eigenvalue of the loss Hessian, known as the sharpness. Recent work has shown that curvature information undergoes complex dynamics during training. We analyze the closed-loop feedback effect between learning rate tuning and curvature.
  arXiv  Detail & Related papers  (2024-07-08T17:56:00Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Predicting Emergent Abilities with Infinite Resolution Evaluation [85.89911520190711]
  We introduce PassUntil, an evaluation strategy with theoretically infinite resolution, through massive sampling in the decoding phase. We predict the performance of the 2.4B model on code generation with merely 0.05% deviation before training starts. We identify a kind of accelerated emergence whose scaling curve cannot be fitted by standard scaling law function.
  arXiv  Detail & Related papers  (2023-10-05T02:35:00Z)
• Uncovering mesa-optimization algorithms in Transformers [61.06055590704677]
  Some autoregressive models can learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. We show that standard next-token prediction error minimization gives rise to a subsidiary learning algorithm that adjusts the model as new inputs are revealed. Our findings explain in-context learning as a product of autoregressive loss minimization and inform the design of new optimization-based Transformer layers.
  arXiv  Detail & Related papers  (2023-09-11T22:42:50Z)
• Uncovering the Hidden Cost of Model Compression [43.62624133952414]
  Visual Prompting has emerged as a pivotal method for transfer learning in computer vision. Model compression detrimentally impacts the performance of visual prompting-based transfer. However, negative effects on calibration are not present when models are compressed via quantization.
  arXiv  Detail & Related papers  (2023-08-29T01:47:49Z)
• Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning [0.0]
  Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels.<n>Noise-robust loss functions have emerged as a notable strategy to counteract this issue, but it remains challenging to create a robust loss function which is not susceptible to underfitting.<n>We propose a novel method denoted as logit bias, which adds a real number $epsilon$ to the logit at the position of the correct class.
  arXiv  Detail & Related papers  (2023-06-08T18:38:55Z)
• Meta-Learning Adaptive Loss Functions [12.182683996452525]
  Loss function learning aims to automate the task of designing a loss function for a machine learning model.<n>We propose a new loss function learning technique for adaptively updating the loss function online after each update to the base model parameters.
  arXiv  Detail & Related papers  (2023-01-30T19:22:46Z)
• Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism [65.46524775457928]
  offline reinforcement learning seeks to utilize offline/historical data to optimize sequential decision-making strategies. We study the statistical limits of offline reinforcement learning with linear model representations.
  arXiv  Detail & Related papers  (2022-03-11T09:00:12Z)
• A Loss Curvature Perspective on Training Instability in Deep Learning [28.70491071044542]
  We study the evolution of the loss Hessian across many classification tasks in order to understand the effect curvature of the loss has on the training dynamics. Inspired by the conditioning perspective, we show that learning rate warmup can improve training stability just as much as batch normalization.
  arXiv  Detail & Related papers  (2021-10-08T20:25:48Z)
• A Mathematical Analysis of Learning Loss for Active Learning in Regression [2.792030485253753]
  This paper develops a foundation for Learning Loss which enables us to propose a novel modification we call LearningLoss++. We show that gradients are crucial in interpreting how Learning Loss works, with rigorous analysis and comparison of the gradients between Learning Loss and LearningLoss++. We also propose a convolutional architecture that combines features at different scales to predict the loss. We show that LearningLoss++ outperforms in identifying scenarios where the model is likely to perform poorly, which on model refinement translates into reliable performance in the open world.
  arXiv  Detail & Related papers  (2021-04-19T13:54:20Z)
• Extreme Memorization via Scale of Initialization [72.78162454173803]
  We construct an experimental setup in which changing the scale of initialization strongly impacts the implicit regularization induced by SGD. We find that the extent and manner in which generalization ability is affected depends on the activation and loss function used. In the case of the homogeneous ReLU activation, we show that this behavior can be attributed to the loss function.
  arXiv  Detail & Related papers  (2020-08-31T04:53:11Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• The Break-Even Point on Optimization Trajectories of Deep Neural Networks [64.7563588124004]
  We argue for the existence of the "break-even" point on this trajectory. We show that using a large learning rate in the initial phase of training reduces the variance of the gradient. We also show that using a low learning rate results in bad conditioning of the loss surface even for a neural network with batch normalization layers.
  arXiv  Detail & Related papers  (2020-02-21T22:55:51Z)

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.