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.

168,657 papers · 148 categories

Trend · papers per month

69139208277 · Jun 202019922001200920172026
48 results for scaling

New scaling framework for MoE architectures ensures stability and optimal performance at scale.

problem Lack of principled understanding of how hyperparameters should scale in MoE architectures.
method Developed a novel Dynamical Mean Field Theory (DMFT) for three scaling regimes of MoE architectures.
result Derived Maximally Scale-Stable Parameterization (MSSP) for SGD and Adam, providing robust learning rate transfer and monotonic improvement with scale.

New principles needed for scaling large language models, challenging traditional regularization methods.

problem The shift from generalization to scaling in machine learning requires new guiding principles.
method Examining the effectiveness of traditional regularization methods in the scaling-centric era.
result Traditional principles of regularization may not generalize to larger scales, highlighting new phenomena like scaling law crossover.

Improves U-Net for scale equivariance in semantic segmentation.

problem Improving generalization in semantic segmentation tasks with varying scales.
method Introduces Scale Equivariant U-Net (SEU-Net) with carefully applied subsampling and upsampling layers and scale-equivariant layers.
result Significantly improved generalization to different scales compared to U-Net and scale-equivariant architecture without upsampling.

New scaling laws optimize model size, training, and inference for better performance.

problem Trade-off between model size and inference cost in modern LLMs.
method Train-to-Test (T2T^2) scaling laws that jointly optimize model size, training tokens, and inference samples.
result Optimal pretraining decisions shift into overtraining regime, leading to stronger performance.

CrossAD detects anomalies in time series data by considering cross-scale associations and cross-window modeling.

problem Anomaly detection in time series data is challenging due to varying patterns at different scales and fixed window sizes.
method CrossAD incorporates cross-scale reconstruction and a query library to capture dynamic cross-scale associations and comprehensive context.
result CrossAD achieves state-of-the-art performance in anomaly detection across multiple real-world datasets.

We define the intrinsic scale at which a network begins to reveal its identity as the scale at which subgraphs in the network (created by a random walk) are distinguishable from similar sized subgraphs in a perturbed copy of the network. We conduct an extensive study of intrinsic scale for several networks, ranging fro…

2019-01-15abs ↗pdf ↗

One of the difficulties of training deep neural networks is caused by improper scaling between layers. Scaling issues introduce exploding / gradient problems, and have typically been addressed by careful scale-preserving initialization. We investigate the value of preserving scale, or isometry, beyond the initial weigh…

2016-04-26abs ↗pdf ↗

We introduce deep scale-spaces (DSS), a generalization of convolutional neural networks, exploiting the scale symmetry structure of conventional image recognition tasks. Put plainly, the class of an image is invariant to the scale at which it is viewed. We construct scale equivariant cross-correlations based on a princ…

2019-05-28abs ↗pdf ↗

The effectiveness of Convolutional Neural Networks (CNNs) has been substantially attributed to their built-in property of translation equivariance. However, CNNs do not have embedded mechanisms to handle other types of transformations. In this work, we pay attention to scale changes, which regularly appear in various t…

2019-10-14abs ↗pdf ↗

Unified scaling laws reveal how model size and training time impact neural network performance.

problem Understanding how much performance improvement can be expected from scaling model size or data volume.
method Established scale-time equivalence and combined it with a linear model analysis of double descent.
result Unified theoretical scaling laws explain previously unexplained phenomena and offer a more accessible path to training large models.

This paper reviews some of the phenomenological models which have been introduced to incorporate the scaling properties of financial data. It also illustrates a microscopic model, based on heterogeneous interacting agents, which provides a possible explanation for the complex dynamics of markets' returns. Scaling and m…

2000-07-25abs ↗pdf ↗

Preprocessing data is an important step before any data analysis. In this paper, we focus on one particular aspect, namely scaling or normalization. We analyze various scaling methods in common use and study their effects on different statistical learning models. We will propose a new two-stage scaling method. First, w…

2017-09-02abs ↗pdf ↗

Optimizer choice affects neural scaling laws, changing the exponent α\alpha.

problem The exponent α\alpha in neural scaling laws L(N)NαL(N) \propto N^{-\alpha} varies with the optimizer used.
method Controlled random-feature regression experiments with five optimizer variants and six spectral conditions.
result Preconditioned optimizers yield steeper scaling (larger α\alpha), with the α\alpha-shift increasing across most of the tested spectral range.

Model shows feature learning can improve neural scaling laws for hard tasks.

problem Understanding and improving neural network scaling laws for various task difficulties.
method Developed a solvable model of neural scaling laws, identified three scaling regimes, and demonstrated feature learning's impact on scaling exponents.
result Feature learning can improve scaling with training time and compute for hard tasks, nearly doubling the exponent.

Analyzed US firm data 1970-2019, identifying scale effects and distributional forms.

problem Understanding differences between small and large firms over time.
method Examined all public US firms, used stylized facts and DLN distribution analysis.
result Small firms are systematically different from large firms, with scale-dependent heteroskedasticity.

Classical scaling is shown to be optimal under various noisy conditions.

problem Consistency of classical scaling under general noise conditions.
method Established using finite fourth moments of noise, derived convergence rates, and matching minimax lower bounds.
result Classical scaling achieves minimax optimality in recovering true configuration from noisy dissimilarities.

This work explores variably scaled kernels to improve non-stationary Gaussian processes.

problem Limited ability of stationary kernels to represent heterogeneous correlation structures.
method Introduces variably scaled kernels to modify correlation structures explicitly.
result Improved reconstruction accuracy and better uncertainty estimates for non-stationary data.

Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences…

2019-02-15abs ↗pdf ↗

New learning dynamics achieve fast convergence in games without needing to know utility scales.

problem Fast convergence guarantees in learning games require prior knowledge of utility scales.
method Developed scale-free and scale-invariant learning dynamics using optimistic follow-the-regularized-leader with adaptive learning rates and clipping techniques.
result Achieved fast convergence rates to Nash and correlated equilibria without prior utility scale knowledge.

Paper introduces multi-scale methods to improve CATE estimation from EO data.

problem Challenges in balancing fine-grained and contextual information in EO-based causal inference.
method Multi-Scale Representation Concatenation, combining Vision Transformer and Causal Forests.
result Multi-scale approach captures effect heterogeneity better than single-scale models.

This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables a…

2018-05-16abs ↗pdf ↗

AutoScale improves LLM pre-training by adjusting data mixtures at different scales.

problem Data mixtures that work well at small scales may not perform as well at larger scales.
method AutoScale uses a two-stage approach: fitting a model to predict loss under different compositions and extrapolating optimal compositions to larger scales.
result AutoScale accelerates convergence and improves downstream performance.

High-dimensional shrinkage risk depends on the default prior for the common scale.

problem Choosing the default prior for the common scale in high-dimensional shrinkage.
method Using radial-power benchmark to compare variance-flat and standard deviation-flat priors.
result The standard deviation-flat prior has a one-unit asymptotic risk advantage near the origin.

New phases identified in neural scaling laws with compute limits.

problem Understanding neural scaling laws under compute constraints.
method Solved neural scaling model with stochastic gradient descent, derived loss curves, analyzed model-parameter-count phases.
result Identified 4 phases (+3 subphases) in data-complexity/target-complexity phase-plane, derived exponents.

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.

Spectral clustering algorithms typically require a priori selection of input parameters such as the number of clusters, a scaling parameter for the affinity measure, or ranges of these values for parameter tuning. Despite efforts for automating the process of spectral clustering, the task of grouping data in multi-scal…

2019-02-06abs ↗pdf ↗

Temperature scaling improves model uncertainty but not diversity in LLMs.

problem Improving the calibration and stochasticity of probabilistic models.
method Investigates theoretical properties of temperature scaling in classification and LLMs.
result Temperature scaling increases model uncertainty but not diversity in LLMs.

Study how large-scale flows align small-scale vortices in 3D Euler equations.

problem Understanding how large-scale flows align small-scale vortices in 3D Euler equations.
method Constructing a Lagrangian coordinate to identify when the Lie bracket is zero and investigating the locality of the pressure term.
result Clarified conditions under which small-scale vortices are aligned by large-scale flows.