The ability to accurately predict the fit of fashion items and recommend the correct size is key to reducing merchandise returns in e-commerce. A critical prerequisite of fit prediction is size normalization, the mapping of product sizes across brands to a common space in which sizes can be compared. At present, size n…
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
48 results for “Size Generalization”
The paper investigates why GNNs struggle to generalize from small to large graphs.
problem Challenges in graph neural networks' ability to generalize across different graph sizes.
method Identified and studied the effect of local structure on size generalization; proposed a novel SSL task.
result GNNs can converge to non-generalizing solutions when there is a discrepancy in local structure.
Polyak step size GD reaches final radius of convergence after log iterations.
problem Statistical and computational complexities of Polyak step size GD.
method Generalized smoothness and Lojasiewicz conditions, stability of gradients.
result Polyak step size GD reaches final statistical radius of convergence after logarithmic number of iterations.
Adaptive batch size schedules improve language model training efficiency and generalization.
problem Dilemma of choosing batch sizes in large-scale model training.
method General-purpose adaptive batch size schedules compatible with data and model parallelism.
result Adaptive batch size schedules outperform constant batch sizes and heuristic warmup schedules.
AdAdaGrad optimizes batch sizes for deep learning models, reducing the generalization gap.
problem The generalization gap between large-batch and small-batch training in deep learning.
method AdAdaGrad introduces adaptive batch size strategies derived from adaptive sampling methods.
result AdAdaGradNorm converges to a first-order stationary point with a rate of O(1/K) in K iterations.
New neural network models learn symmetric functions of varying input sizes.
problem Learning symmetric functions with varying input sizes.
method Functional perspective on neural networks, treating symmetric functions as functions over probability measures.
result Established approximation and generalization bounds for shallow architectures that extend across input sizes.
Existing research shows that the batch size can seriously affect the performance of stochastic gradient descent~(SGD) based learning, including training speed and generalization ability. A larger batch size typically results in less parameter updates. In distributed training, a larger batch size also results in less fr…
Empirical study on SGD hyperparameters and adversarial robustness.
problem Effect of SGD hyperparameters on adversarial robustness and generalization.
method Empirical observation of learning rate, batch size, and momentum effects on adversarial robustness and generalization.
result Constant learning rate to batch size ratio leads to good generalization and almost constant adversarial robustness.
Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methodsstat.ML
Adaptive batch sizes improve local gradient methods in distributed training.
problem Communication bottlenecks in distributed deep learning.
method Adaptive batch size strategies for local gradient methods.
result Adaptive batch sizes reduce minibatch gradient variance and improve training efficiency.
Pruning improves model generalization in over-parameterized models, contradicting traditional theories.
problem Pruning's effect on generalization in over-parameterized models.
method Empirical study on standard pruning algorithms and additional regularization effects.
result Pruning leads to better training and regularization, improving generalization.
Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer more parallelism and hence better computational efficiency. We have developed a n…
Develops a generalized version of Chung's Lemma for stochastic optimization methods.
problem Establishing asymptotic convergence rates for stochastic optimization methods under various step size rules.
method Generalized version of Chung's Lemma for a broader family of step size rules.
result Demonstrates tight non-asymptotic convergence rates for various stochastic methods.
The paper introduces the concept of a cluster structure to define a joint distribution of the sample size and its exchangeable random partitions. The cluster structure allows the probability distribution of the random partitions of a subset of the sample to be dependent on the sample size, a feature not presented in a …
We obtain the first positive results for bounded sample compression in the agnostic regression setting with the loss, where . We construct a generic approximate sample compression scheme for real-valued function classes exhibiting exponential size in the fat-shattering dimension but independen…
A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizescs.LG
Standard optimizers perform as well as LARS and LAMB at large batch sizes.
problem Comparing optimizers for neural network training at large batch sizes.
method Used standard optimizers like Nesterov momentum and Adam to match or exceed LARS and LAMB results.
result Standard optimizers can match or exceed LARS and LAMB at large batch sizes.
Study ridge ensembles in proportional feature-to-sample size regime, proving risk equivalence and GCV consistency.
problem Characterizing and optimizing ridge ensembles in proportional feature-to-sample size regimes.
method Proportional asymptotics analysis, GCV for tuning, proving risk equivalence.
result Risk of optimal full ridgeless ensemble matches optimal ridge predictor's risk.
Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.…
Downsampling can improve generalization in ridgeless linear regression, especially with optimal sketching size.
problem Improving generalization in ridgeless linear regression with limited data.
method Investigating the effects of downsampling on the sketched ridgeless least square estimator in the proportional regime.
result Optimal sketching size minimizes out-of-sample prediction risks and stabilizes risk curves.
New kernel model scales to large datasets.
problem Challenges in scaling kernel machines to large datasets.
method Introduced EigenPro 3.0, an algorithm based on projected dual preconditioned SGD.
result Ability to scale model and data sizes independently.
The paper improves methods for estimating set size using samples.
problem Estimating the size of a set from a uniform sample.
method Refines estimators using the birthday problem and maximum of sample.
result Develops a general theory for non-asymptotic error bounds.
Proposes a differentiable hypergeometric distribution for learning group importance.
problem Learning the sizes of subsets in applications like clustering and weakly-supervised learning.
method Introduces a reparameterizable hypergeometric distribution to model group sizes and learn their relative importance.
result Outperforms previous methods in weakly-supervised learning and clustering.
This paper explores how effective sample size, dimensionality, and model performance are related in covariate shift adaptation.
problem Understanding the relationship between effective sample size, dimensionality, and generalization in covariate shift adaptation.
method Building a unified theory connecting effective sample size, data dimensionality, and generalization in the context of covariate shift adaptation.
result Dimensionality reduction or feature selection can increase effective sample size, supporting the practice of reducing dimensionality before covariate shift adaptation.
The study reveals a transition in neural network performance from infinite-width to variance-limited behavior as dataset size increases.
problem Understanding the transition from infinite-width to variance-limited behavior in neural networks.
method Empirical study of the transition from infinite-width to variance-limited behavior as a function of sample size and network width.
result The critical sample size \( P^* \) is approximately \( \sqrt{N} \) for polynomial regression with ReLU networks.
In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet few algorithms have been developed for setting the step-size automatically for TD learning. An important limitation of current methods is that…
We study the sample complexity of private synthetic data generation over an unbounded sized class of statistical queries, and show that any class that is privately proper PAC learnable admits a private synthetic data generator (perhaps non-efficient). Previous work on synthetic data generators focused on the case that …
New method for MMD with unequal sample sizes improves test power.
problem Existing MMD methods assume equal sample sizes, discarding valuable data.
method Extended generalized U-statistics to handle unequal sample sizes.
result New asymptotic distributions and power optimization for MMD with unequal sample sizes.
New findings cast doubt on the role of in generalizing neural networks.
problem The role of in neural network generalization remains unclear.
method Experiments with various training interventions and batch sizes.
result Generalization benefits can vanish at larger batch sizes, challenging the role of .
Adaptive SGD learns optimal batch size for strong convex functions.
problem Finding optimal batch size for SGD in practice.
method Adaptive SGD method that learns optimal batch size.
result Adaptive SGD exhibits nearly optimal performance in experiments.
Scaling laws found for reinforcement learning performance with model size and compute.
problem Challenges in extending generative modeling scaling laws to reinforcement learning.
method Introduced intrinsic performance as a monotonic function of mean episode return.
result Intrinsic performance scales as a power law in model size and environment interactions.
We investigate the dynamical and convergent properties of stochastic gradient descent (SGD) applied to Deep Neural Networks (DNNs). Characterizing the relation between learning rate, batch size and the properties of the final minima, such as width or generalization, remains an open question. In order to tackle this pro…
We consider two questions at the heart of machine learning; how can we predict if a minimum will generalize to the test set, and why does stochastic gradient descent find minima that generalize well? Our work responds to Zhang et al. (2016), who showed deep neural networks can easily memorize randomly labeled training …
Paper overcomes sample size barrier in reinforcement learning with generative models.
problem Sample efficiency in reinforcement learning with generative models.
method Developed two algorithms to certify minimax optimality of sample complexity.
result Achieved minimax-optimal guarantees for a wide range of sample sizes.
New algorithms verify and search causal graphs with minimal interventions.
problem Recovering causal graphs from interventional data.
method Characterization of minimal intervention sets for verification, and adaptive graph separator algorithm for search.
result First provable algorithms for efficient verification and search of causal graphs.
Negative step sizes improve second-order methods for neural networks.
problem Second-order methods discard negative curvature, limiting their effectiveness.
method Introduce negative step sizes in second-order methods combined with Wolfe line search.
result Negative step sizes lead to global convergence and improved performance.
Most generative models for clustering implicitly assume that the number of data points in each cluster grows linearly with the total number of data points. Finite mixture models, Dirichlet process mixture models, and Pitman--Yor process mixture models make this assumption, as do all other infinitely exchangeable cluste…
This paper characterizes projective models in statistical relational learning.
problem Projectivity in statistical relational models is beneficial for inference and learning.
method Representation theorems for infinite exchangeable arrays to characterize projective models.
result A class of directed graphical latent variable models correspond to projective relational models.
Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on properties of the optimization algorithm, including acceleration and preconditioning, thr…
Gradient descent with large steps leads to chaotic parameter space and unpredictable outcomes.
problem Understanding the behavior of gradient descent with large step sizes in matrix factorization.
method Analyzing the fractal structure of the parameter space and deriving critical step sizes for convergence.
result Gradient descent with large steps exhibits chaotic behavior and sensitivity to initialization, creating a fractal boundary between converging and diverging minimizers.
This paper explores the limits of large batch sizes in deep learning.
problem Understanding the optimal batch size for deep learning models.
method Detailed numerical optimization and experimental analysis of large batch sizes.
result Improvement of 18% top-1 test accuracy with an optimized batch size recipe.
Deep neural networks can approximate complex functions through repeated compositions of a fixed-size ReLU network.
problem Understanding the expressive power of deep neural networks through function compositions.
method Demonstrated the surprising expressive power of repeated compositions of a single fixed-size ReLU network.
result Repeated compositions of a single fixed-size ReLU network can approximate 1-Lipschitz continuous functions on with an error .
Improved variance reduction for Riemannian non-convex optimization with adaptive batch size.
problem Optimizing non-convex functions on Riemannian manifolds.
method Batch size adaptation in R-SVRG, R-SRG, and R-SPIDER.
result Achieves lower total complexities for various non-convex functions.
Study on typical knots and links using grid diagrams, focusing on size, components, and writhe.
problem Understanding the statistical behavior of knots and links, especially their typical properties.
method Modeling knots and links with grid diagrams, examining three invariants: size, components, and writhe, through numerical analysis.
result The size of a random knot is uniformly distributed and linearly dependent on grid size, while the number of components follows a distribution whose mean and variance grow with log_2 of grid size.
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.
Adam optimizer's bias is influenced by mini-batch size and momentum hyperparameters.
problem Understanding how Adam's implicit bias is affected by mini-batch size and momentum parameters.
method Theoretical framework to analyze mini-batch noise's impact on Adam's memory and bias.
result The magnitude of anti-regularization by memory depends on batch size and momentum hyperparameters.
Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Addstat.ML
Synthetic augmentation helps but not always in imbalanced learning.
problem Imbalanced learning causes poor performance on rare classes.
method Developed a statistical framework for synthetic augmentation in imbalanced learning.
result Synthetic augmentation is not always beneficial and depends on the imbalance regime.
Study uses generative models to assess credit risk and determine loan sizes in e-commerce supply chain finance.
problem Credit risk assessment and loan size determination for small- and medium-sized sellers in e-commerce supply chain finance.
method Proposes a unified framework using Quantile-Regression-based Generative Metamodeling (QRGMM) integrated with Deep Factorization Machines (DeepFM) to capture complex covariate interactions in e-commerce sales data.
result Validates the model's efficacy for credit risk assessment and loan size determination on synthetic and real-world data.
Alignment of neural network representations is influenced by SNR and sample size.
problem Understanding how neural network representations align across different conditions.
method Controlled training of neural networks on perturbed datasets, analyzing alignment and generalization.
result Alignment varies monotonically with SNR but non-monotonically with sample size, with minimal alignment near the interpolation threshold.
Reduces multiclass and regression compression schemes to binary ones.
problem Developing efficient learning algorithms for multiclass and regression problems.
method Reduces sample compression schemes for binary classes to multiclass and regression settings.
result Establishes new compression schemes for multiclass and regression problems.