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

73145218290 · Jun 202019922001200920172026
48 results for angle decay rates

Study precise rates of horizontal gap shrinkage on generic translation surfaces.

problem Understanding precise decay rates of horizontal gaps in translation surfaces.
method Analyzing saddle connections and their angles on translation surfaces.
result Obtained precise decay rates for the difference in angle between almost horizontal saddle connections.

Quantum 6j6j-symbols linked to tetrahedra angles and volumes.

problem Understanding quantum 6j6j-symbols and their geometric interpretation.
method Establishing the geometric connection between quantum 6j6j-symbols and tetrahedra angles, including spherical, Euclidean, and hyperbolic cases.
result Quantum 6j6j-symbols correspond to dihedral angles of specific tetrahedra, including generalized hyperbolic ones, with exponential growth rates tied to their volumes.

The paper studies Teichmüller TQFT for hyperbolic knots, proving exponential decay of partition functions.

problem Analyzing Teichmüller TQFT for hyperbolic knots with generalized FAMED triangulations.
method Introducing generalized FAMED property, proving exponential decay of partition functions in semi-classical limit.
result Partition functions decay exponentially with the volume of knot complements, and the 1-loop invariant emerges.

Optimal learning rates decay to zero in easy tasks and maintain a warmup phase in hard tasks.

problem Optimizing learning rates under functional scaling laws for model training.
method Deriving optimal learning-rate schedules based on exponents ss and ββ.
result Sharp phase transition between easy and hard tasks, with different decay behaviors.

Study on massless Vlasov equation on Reissner-Nordström spacetimes, showing decay rates and non-decay phenomena.

problem Analyzing decay and non-decay rates of solutions to the massless Vlasov equation on Reissner-Nordström spacetimes.
method Quantitative analysis of geodesic flow and comparison to wave equation instability results.
result Exponential decay rates in subextremal cases and polynomial rates in extremal cases, with non-decay of transversal derivatives in extremal cases.

WSD schedule improves model training efficiency by adapting learning rates dynamically.

problem Fixed compute budgets limit training efficiency of language models.
method Introduces a WSD schedule that uses a constant learning rate followed by a rapid decay phase.
result WSD schedule generates a non-traditional loss curve with stable and decay phases.

Step decay schedules improve convergence in non-convex optimization.

problem Improving convergence in non-convex optimization problems.
method Analyzing convergence rates of step decay schedules in non-convex, convex, and strongly convex problems.
result Step decay schedules achieve O(lnT/T)\mathcal{O}(\ln T/\sqrt{T}) convergence rates in various optimization scenarios.

The paper studies harmonic map heat flow stability and decay rates.

problem Analyzing stability and decay rates of harmonic map heat flow solutions.
method Use of homogeneous Besov space B˙p,dp(Rd)\dot{B}^{\frac{d}{p}}_{p,\infty}(\mathbb{R}^d) for small initial data and self-similar decay assumption.
result Decay rates for solutions of the harmonic map flow of the form ablau(t)L(Rd)Ct12\| abla u(t) \|_{L^\infty(\mathbb{R}^d)}\leq Ct^{-\frac12} and self-similar decay under stronger initial conditions.

Learning rate decay (lrDecay) is a \emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empirically observed to help both optimization and generalization. Common beliefs in how lrDecay works come from the optimization analysis of (S…

2019-08-05abs ↗pdf ↗

Active data collection improves convergence rates in operator learning.

problem Improving convergence rates in operator learning with linear target and stochastic input.
method Active data collection strategies with mean-zero stochastic process and continuous covariance kernels.
result Achieves arbitrarily fast error convergence rates with eigenvalue decay of covariance kernels.

Model proposes neural network for continuous time dynamics with inductive biases.

problem Training neural networks for small datasets with nonlinear dynamics.
method Inductive biases on decay rates and frequencies using Koopman operator theory.
result Higher forecasting performance with single short training sequence.

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.

We determine the factorial growth rate of the number of finite index subgroups of right-angled Artin groups as a function of the index. This turns out to depend solely on the independence number of the defining graph. We also make a conjecture for right-angled Coxeter groups and prove that it holds in a limited setting…

2018-05-10abs ↗pdf ↗

In this paper, we give a new sharp generalization bound of lp-MKL which is a generalized framework of multiple kernel learning (MKL) and imposes lp-mixed-norm regularization instead of l1-mixed-norm regularization. We utilize localization techniques to obtain the sharp learning rate. The bound is characterized by the d…

2011-03-27abs ↗pdf ↗

Riemannian stochastic gradient descent converges faster with increasing batch size.

problem Improving convergence rate of Riemannian stochastic gradient descent.
method Theoretical analysis and numerical investigation of increasing batch size effects.
result Riemannian stochastic gradient descent converges faster with increasing batch size.

The study examines Kernel Ridge Regression error rates across noiseless and noisy conditions.

problem Characterizing Kernel Ridge Regression error rates in different noise levels.
method Unified analysis of Kernel Ridge Regression under various noise and regularization conditions.
result A crossover from noiseless to noisy error rates is observed as sample complexity increases.

Paper calculates eigenvalue decay rates for neural network kernels on general domains.

problem Determining eigenvalue decay rates for neural network kernels on arbitrary domains.
method Proved dynamics of wide neural networks approximates NTK on general domains, used minimax optimality and interpolation spaces.
result Provided strategy to calculate eigenvalue decay rates for neural network kernels.

AdamNX improves Adam's stability by adjusting its learning rate.

problem Adam's tendency to converge to non-flat minima in large-scale models.
method Proposes a novel exponential decay mechanism for Adam's second-order moment estimate.
result AdamNX outperforms Adam and its variants in stability and performance.

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.

Momentum is a widely used technique for gradient-based optimizers in deep learning. In this paper, we propose a decaying momentum (\textsc{Demon}) rule. We conduct the first large-scale empirical analysis of momentum decay methods for modern neural network optimization, in addition to the most popular learning rate dec…

2019-10-11abs ↗pdf ↗

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 ↗

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.

WSqD extends learning rate schedules for large model training without fixed horizons.

problem Fixed learning rate schedules limit training horizon extension.
method WSqD replaces constant stable phase with a shifted inverse-square-root base, retaining linear cooldown.
result WSqD achieves minimax-optimal convergence rate and horizon-independence.

Paper tackles dynamic pricing in a geometrically decaying environment, achieving better occupancy with lower rates.

problem Minimizing expected loss in a dynamically changing environment with decisions dependent on the data distribution.
method Introduces algorithms for information and loss function settings, using repeated decision deployment to allow mixing of the environment.
result Iteration complexity matches first and zero order stochastic gradient methods up to logarithmic factors.

SignSGD outperforms SGD in linear regression with optimal scaling laws under PLRF model.

problem Improving linear regression performance with signSGD under power-law random features.
method Analysis of signSGD risk under PLRF model, comparison with SGD, identification of unique effects.
result SignSGD can have a steeper compute-optimal slope than SGD in noisy regimes, especially with WSD schedule.

The paper presents a multi-power law for predicting loss curves across different learning rate schedules.

problem Understanding and optimizing the relationship between model performance and hyperparameters, especially learning rates.
method Proposes a multi-power law that combines power laws based on the sum of learning rates and additional laws for loss reduction due to decay.
result The multi-power law accurately predicts loss curves for unseen learning rate schedules and finds a schedule that outperforms cosine learning rate.

We discover scaling laws for kernel regression loss under various learning rate schedules.

problem Understanding loss dynamics and learning rate schedules in kernel regression.
method Theoretical analysis of stochastic gradient descent on a power-law kernel regression model.
result Established a Functional Scaling Law (FSL) capturing the full loss trajectory under arbitrary learning rate schedules.

One knows that the large time heat decay exponent on a nilpotent group is given by half the growing rate of the volume of its large balls. This work deals with the similar problem of trying to interpret geometrically the heat decay on (one) forms. We will show how it is (partially) related to the depth of the relations…

2001-12-06abs ↗pdf ↗

Paper develops an online learning algorithm for functional data models.

problem Recovering slope functions or predictors in functional data models.
method Online regularized learning algorithm in reproducing kernel Hilbert spaces with polynomially decaying step-size.
result Established fast convergence rates for estimation error without capacity assumption.

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.