Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

63127190253 · Jun 202019922001200920172026
48 results for token-level weight decay

Language models allocate information storage, not collapsing into uniform representations.

problem Incomplete neural collapse in language model representations.
method Analyzing variance and information sharing across 14 models, proving an information floor.
result Within-class variance is allocated information storage, not collapsed into uniform representations.

Weight decay stabilizes training dynamics by slowing progressive sharpening.

problem Understanding how weight decay affects training stability in deep learning models.
method Analyzing weight decay effects at the Edge of Stability, developing a mathematical framework.
result Weight decay dampens oscillations and stabilizes sharpness in CNNs, causing a phase transition in MLPs.

SGD and weight decay encourage neural networks to learn low-rank weight matrices.

problem The bias of SGD towards low-rank weight matrices in neural networks.
method The study investigates the effect of SGD and weight decay on the rank of weight matrices in neural networks, both theoretically and empirically.
result Training with SGD and weight decay induces a bias towards rank minimization in weight matrices, which becomes more pronounced with smaller batch sizes and stronger weight decay.

Topic models are typically evaluated with respect to the global topic distributions that they generate, using metrics such as coherence, but without regard to local (token-level) topic assignments. Token-level assignments are important for downstream tasks such as classification. Even recent models, which aim to improv…

2019-05-18abs ↗pdf ↗

Proposes integrating global and local entropy for more reliable LLMs.

problem Uncertainty in large language models (LLMs) leads to unreliable predictions.
method Measures global uncertainty from hidden-state matrices and local uncertainty from tokens, combining them via a multiplicative gate.
result Global-Local Uncertainty (GLU) outperforms unsupervised baselines across multiple models and benchmarks.

Study on optimal ReLU networks with weight decay for interpolation.

problem Interpolating data with radially symmetric distributions using shallow ReLU networks.
method Weight decay regularization in infinite neuron, infinite data limit; analysis of growth rates.
result Existence and growth rates of unique radially symmetric minimizers with weight decay.

Novel Adam-family method with decoupled weight decay for training neural networks.

problem Training nonsmooth neural networks with weight decay.
method Proposes a novel Adam-family method with decoupled weight decay, establishing convergence properties and demonstrating superior performance.
result Asymptotically approximates SGD and enhances generalization performance.

Weight decay is one of the standard tricks in the neural network toolbox, but the reasons for its regularization effect are poorly understood, and recent results have cast doubt on the traditional interpretation in terms of L2L_2 regularization. Literal weight decay has been shown to outperform L2L_2 regularization for…

2018-10-29abs ↗pdf ↗

This paper reveals periodic behavior in neural network training with BN and weight decay.

problem Understanding the dynamics of neural network training with BN and weight decay.
method Rigorous investigation of empirical and theoretical mechanisms.
result Periodic behavior in training is a generalization of previously opposing perspectives.

Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular regularization algorithms is to impose L-2 penalty on the model parameters resulting in the decay of parameters, called weight-decay, and the …

2019-07-21abs ↗pdf ↗

This research tackles uncertainty estimation in autoregressive structured prediction tasks.

problem Ensuring safety and robustness of AI systems through accurate uncertainty estimation.
method Develops a unified probabilistic ensemble-based framework for token-level and sequence-level uncertainty estimation.
result Provides baselines for error and out-of-domain detection on translation and speech recognition datasets.

Adam's generalization performance is improved by batch size and weight decay in neural networks.

problem Understanding how batch size and weight decay affect Adam's generalization in neural networks.
method Theoretical analysis of two-layer over-parameterized CNNs on image data.
result Adam's mini-batch variants can achieve near-zero test error, unlike full-batch Adam.

Weibull weight-scale parameter λλ evolves during AdamW training, with alignment, injection, and decay forces driving its growth and relaxation.

problem Understanding the evolution of the Weibull weight-scale parameter λλ during AdamW training.
method Deriving a leading-order three-force decomposition of the squared weight norm from AdamW updates.
result The alignment force dominates the rise phase, contributing 88-94% of the absolute force budget across four random seeds.

The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on …

2019-04-24abs ↗pdf ↗

The paper connects neural collapse and low-rank bias in networks with L2 regularization.

problem Understanding the emergence of low-rank bias and neural collapse in L2-regularized networks.
method Unified theoretical framework linking TCV and rank of weight matrices, proving global optimality of DNC1, and establishing a benign landscape property.
result Zero TCV across intermediate layers minimizes representation cost under natural architectural constraints, and DNC1 is globally optimal.

Adaptive weights improve physics-informed neural networks and deep operator networks.

problem Training physics-informed neural networks and deep operator networks can be challenging, leading to unsatisfactory accuracy and efficiency.
method Proposes a pointwise adaptive weighting method that balances the residual decay rate across different training points.
result Our proposed approach of balanced residual decay rates offers advantages including bounded weights, high prediction accuracy, fast convergence rate, low training uncertainty, low computational cost, and ease of hyperparameter tuning.

This paper investigates the effectiveness of decoupled weight decay at the start of training.

problem The traditional approach to weight decay is not effective throughout training.
method The authors investigate decoupled weight decay, applying it only at the start of training.
result Applying weight decay only at the start of training stabilizes network weights and improves performance.

Study reveals dynamics of neural networks with normalization, weight decay, and SGD.

problem Understanding the equilibrium condition in Spherical Motion Dynamics (SMD).
method Investigates SMD by exploring the cause of equilibrium condition, introducing assumptions, proposing angular update, and verifying theoretical results.
result Proves weight norm and angular update can converge at linear rate under given assumptions.

This paper examines weight initialization for 1-Lipschitz networks to improve robustness against adversarial attacks.

problem Improving the robustness of deep neural networks against adversarial attacks.
method Examined weight parametrization of AOL and SLL networks, calculated weight variance bounds, and demonstrated weight decay.
result Weight initialization causes deep 1-Lipschitz networks to decay to zero, and weight variance does not affect output variance distribution.

We introduce a new weight-decay scaling rule to maintain sublayer gains across different widths in modern scale-invariant architectures.

problem In modern scale-invariant architectures, training quickly enters a steady state where normalization layers create backward scale sensitivity, degrading learning-rate transfer.
method We introduce a weight-decay scaling rule for AdamW that preserves sublayer gain across widths by equalizing the effective learning rate.
result Our empirical weight-decay scaling rule λ2dλ_2\propto \sqrt{d} approximately keeps sublayer gains width invariant, enabling zero-shot transfer of learning rate and weight decay.

This paper analyzes convergence of large-scale Transformers with weight decay.

problem Understanding optimization guarantees in large-scale Transformer training.
method Construct mean-field limit, show gradient flow convergence to PDE, demonstrate global minimum consistency.
result Gradient flow reaches global minimum in large-scale Transformers with small weight decay.

Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness to some perturbations by including them in the training process, but this tends to exacerbate other vulnerabilities of the model. The adversa…

2018-04-10abs ↗pdf ↗

This research integrates attention into XAI frameworks for better model explanations.

problem Improving the interpretability of transformer models.
method Developed two novel explanation methods: Shapley value decomposition and token-level directional derivatives.
result Attention weights can be meaningfully incorporated into XAI frameworks, enhancing transformer explainability.

Generalizes neural tangent kernel analysis for two-layer networks with noise and regularization.

problem Limitations of NTK analysis in deep learning practice.
method Generalized NTK analysis for two-layer neural networks with weight decay and gradient noise.
result Noisy gradient descent with weight decay exhibits 'kernel-like' behavior and converges linearly.

New regularizer improves neural network robustness and generalization.

problem Ineffective weight decay for networks with homogeneous activation functions.
method Proposes an invariant regularizer to penalize intrinsic weight norms.
result Improves generalization and adversarial robustness on various datasets.

Wide neural networks with weight decay exhibit neural collapse.

problem Proving neural collapse in wide neural networks trained with weight decay.
method Generic guarantees on neural collapse for wide networks with weight decay, proving low training error and balancedness, and bounded conditioning.
result First proof of neural collapse in end-to-end training of wide neural networks with weight decay.

Language models perform worse with implicit reward models than explicit ones.

problem Understanding why implicit reward models generalize worse than explicit ones.
method Investigated the root cause of the generalization gap between IM-RMs and EX-RMs.
result Implicit reward models rely more on superficial token-level cues, leading to worse generalization.

Theoretical justification for deep networks' performance with regularization techniques.

problem Understanding the performance of deep networks trained with the square loss.
method Analysis of gradient flow and theoretical justification of regularization techniques.
result Convergence to solutions with smaller Frobenius norms leads to better classification error bounds.

Constructs a support-preserving homotopy for differential forms with boundary decay estimates.

problem Non-uniqueness of chain homotopies in de Rham complexes with boundary decay properties.
method Constructs a specific chain homotopy with desirable support propagation and boundary decay estimates.
result Obtains a support-preserving right inverse of the divergence operator with optimal decay estimates.

The study introduces anytime learning schedules for large language models without fixed horizons.

problem Training large language models without knowing the total training horizon.
method Theoretical analysis and weight averaging to create anytime learning schedules.
result Theoretical and empirical evidence shows that weight averaging with simple step sizes can achieve comparable final loss to well-tuned cosine schedules.

We analyze dropout in deep networks with rectified linear units and the quadratic loss. Our results expose surprising differences between the behavior of dropout and more traditional regularizers like weight decay. For example, on some simple data sets dropout training produces negative weights even though the output i…

2016-02-14abs ↗pdf ↗

DOS improves language model generation by considering inter-token dependencies.

problem Lack of sequence-level information and inter-token dependencies in existing decoding strategies.
method Dependency-Oriented Sampler (DOS) that uses attention matrices to approximate inter-token dependencies.
result DOS consistently achieves superior performance on code generation and mathematical reasoning tasks.

New method for training deep neural networks with regularization, converging to better generalization.

problem Improving generalization of deep neural networks through explicit regularization.
method Regularizer Mirror Descent (RMD) method, inspired by convergence properties of stochastic mirror descent (SMD).
result RMD converges to a point close to the minimizer of the cost function, leading to better generalization performance.

Regularization and data augmentation can be class-dependent, leading to poor performance on some classes.

problem Class-dependent effects of regularization and data augmentation.
method Evaluation of regularization and data augmentation techniques on Imagenet and INaturalist datasets.
result Regularization and data augmentation can lead to significant performance drops on some classes.

Regularizers change the geometric properties of loss functions in neural networks.

problem Understanding how different regularizers affect the geometric properties of loss functions in neural networks.
method Examined several regularizers, including weight decay, to determine if the regularized loss function becomes Morse.
result For certain regularizers, the regularized loss function becomes Morse, indicating a change in geometric properties.

Charmer improves character-level adversarial attacks for language models.

problem Efficiency and effectiveness of character-level adversarial attacks for language models.
method Query-based adversarial attack method that maintains semantic similarity.
result Charmer achieves high attack success rate and similar adversarial examples.