This paper improves generative models by using data scaling and theoretical analysis.
problem Challenges in selecting noise distributions for stable learning in generative models.
method Introduces Scale-GAN, which uses data scaling and variance-based regularization.
result Data scaling controls the bias-variance trade-off and improves stability and accuracy.
Study shows cliff-learning in transfer learning from foundation models.
problem Data-scaling of transfer learning from foundation models in low data regimes.
method Investigation of cliff-learning phenomenon through foundation-model analysis and toy models.
result Cliff-learning reflects compatibility between priors and tasks.
New algorithm STCV improves sparse model discovery from normalised data.
problem Distortion of sparse model discovery due to data scaling.
method STCV, a novel sparse regression algorithm robust to data scaling.
result STCV outperforms standard methods on normalised, noisy datasets.
The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networks. Nevertheless, the functional form of this dependency remains elusive. In this work, we present a functional form which approximates well…
The paper analyzes how repeating epochs affects data scaling in linear regression.
problem Understanding how to scale data for multi-epoch training in linear regression.
method Theoretical analysis of effective reuse rate (E(K, N)) under strong convexity or Zipf-distributed data.
result The effective reuse rate E(K, N) plateaus at a problem-dependent value that grows with N, indicating diminishing marginal gains.
Adding data can sometimes hurt model performance in multi-source healthcare tasks.
problem Identifying when adding more data helps or hinders model outcomes in multi-source healthcare tasks.
method Identified the Data Addition Dilemma, demonstrated empirically observed trade-offs, introduced distribution shift heuristics.
result Adding data can sometimes reduce model performance due to distribution shift.
Global neural networks improve financial forecasting accuracy with larger, diverse datasets.
problem Mixed empirical performance in financial time series forecasting due to local model estimation.
method Global estimation strategy that pools information across cross-sections of over 10,000 global stocks.
result Forecasting accuracy improves with larger and more heterogeneous training datasets.
We propose a new learning to rank algorithm, named Weighted Margin-Rank Batch loss (WMRB), to extend the popular Weighted Approximate-Rank Pairwise loss (WARP). WMRB uses a new rank estimator and an efficient batch training algorithm. The approach allows more accurate item rank approximation and explicit utilization of…
We present new findings in regard to data analysis in very high dimensional spaces. We use dimensionalities up to around one million. A particular benefit of Correspondence Analysis is its suitability for carrying out an orthonormal mapping, or scaling, of power law distributed data. Power law distributed data are foun…
Paper compares ML methods for credit scoring, highlighting feature selection and scaling impacts.
problem Determining default risk in credit scoring models.
method Eight ML methods (SVM, Naive Bayes, DT, RF, XGBoost, KNN, MLP, LR) with feature selection and scaling.
result Feature selection and scaling improve model performance in credit scoring.
With the recent popularity of graphical clustering methods, there has been an increased focus on the information between samples. We show how learning cluster structure using edge features naturally and simultaneously determines the most likely number of clusters and addresses data scale issues. These results are parti…
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.
New method speeds up training of large kernel models.
problem Scaling kernel machines to large datasets and model sizes.
method Delayed projections in Preconditioned Stochastic Gradient Descent (PSGD).
result Significant training speed up over existing methods.
Correlated topic modeling has been limited to small model and problem sizes due to their high computational cost and poor scaling. In this paper, we propose a new model which learns compact topic embeddings and captures topic correlations through the closeness between the topic vectors. Our method enables efficient inf…
A new robust and flexible classification method for non-Gaussian data.
problem Robustness to scale changes and non-Gaussian distributions in classical discriminant analysis.
method FEMDA uses arbitrary Elliptically Symmetrical distributions and scale parameters for each data point.
result FEMDA is robust to scale changes and outperforms other methods.
New methods for Markov Blanket discovery using MML outperform existing approaches.
problem Causal discovery from large datasets.
method Developed three new methods of Markov Blanket discovery using Minimum Message Length.
result Our best MML method is consistently competitive and has advantageous features.
Proposes a non-parametric method for deep discrete latent variable models.
problem Learning sparse discrete latent representations in deep models.
method Iterative algorithm with Beta-Bernoulli process prior and local data scaling.
result Improves sparsity and scalability of deep discrete latent variable models.
In designing personalized ranking algorithms, it is desirable to encourage a high precision at the top of the ranked list. Existing methods either seek a smooth convex surrogate for a non-smooth ranking metric or directly modify updating procedures to encourage top accuracy. In this work we point out that these methods…
Kernel improves Gaussian process scalability for wide datasets.
problem Under-performance of Gaussian processes on wide data.
method Introduces Bézier Gaussian Process kernel with exponential summarising variables growth and linear cost.
result Empirically demonstrates scalability to both tall and wide datasets.
Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this pap…
Develops a VAE model for datasets with missing data.
problem Applying VAEs to datasets with missing data.
method A novel latent variable model of a corruption process generating missing data, with a tractable ELBO.
result Improved marginal log-likelihood and better missing data imputation compared to existing approaches.
New framework minimizes model complexity for improved few-shot learning.
problem Empirical benefits of pre-training scale with data size but lack theoretical explanation.
method Complexity Minimization framework for meta-representation learning.
result Theoretical analysis shows error rate improves with more meta-training data.
Distributed machine learning is an approach allowing different parties to learn a model over all data sets without disclosing their own data. In this paper, we propose a weighted distributed differential privacy (WD-DP) empirical risk minimization (ERM) method to train a model in distributed setting, considering differ…
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 design and mathematically analyze sampling-based algorithms for regularized loss minimization problems that are implementable in popular computational models for large data, in which the access to the data is restricted in some way. Our main result is that if the regularizer's effect does not become negligible as th…
Study shows how anisotropic data affects learning dynamics in phase retrieval.
problem Understanding learning dynamics in phase retrieval with anisotropic Gaussian inputs.
method Developed a tractable reduction to reveal a three-phase trajectory and derived scaling laws.
result Found that anisotropy leads to a three-phase trajectory: fast escape, slow convergence, and spectral-tail learning.
Attributes, such as metadata and profile, carry useful information which in principle can help improve accuracy in recommender systems. However, existing approaches have difficulty in fully leveraging attribute information due to practical challenges such as heterogeneity and sparseness. These approaches also fail to c…
A universal learner achieves best rates for all distributions.
problem Improving learning algorithm rates under various settings.
method Simple extension of Levin's universal search.
result Achieves best-possible rates for all distributions.
A tensor provides a concise way to codify the interdependence of complex data. Treating a tensor as a d-way array, each entry records the interaction between the different indices. Clustering provides a way to parse the complexity of the data into more readily understandable information. Clustering methods are heavily …
Linear classifiers separate the data with a hyperplane. In this paper we focus on the novel method of construction of multithreshold linear classifier, which separates the data with multiple parallel hyperplanes. Proposed model is based on the information theory concepts -- namely Renyi's quadratic entropy and Cauchy-S…
Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However, existing cryptographic protocols still incur excess computational overhead. Here,…
CNFs learn on manifolds using PPD, improving likelihood and sample quality.
problem Training CNFs on manifolds efficiently and accurately.
method Minimizing PPD, a novel divergence, to train CNFs on manifolds.
result CNFs trained with PPD achieve state-of-the-art results on manifold benchmarks.
This work shows that supervised contrastive learning achieves similar results to cross-entropy but requires more iterations.
problem The question of whether there are fundamental differences in representation geometry between supervised contrastive learning and cross-entropy.
method The authors prove that both losses attain their minimum when representations of each class collapse to the vertices of a regular simplex, and they empirically validate this finding.
result Supervised contrastive learning requires more iterations to reach a close-to-optimal state compared to cross-entropy, indicating different optimization behavior.
Sharp analysis of knowledge distillation for high-dimensional regression.
problem Characterizing the risk of target models in high-dimensional settings.
method Sharp non-asymptotic bounds for ridgeless regression under model and distribution shifts.
result Identifies optimal surrogate models and reveals benefits and limitations of discarding weak features.
HSSE framework embeds single-cell RNA-seq data at multiple scales.
problem Capturing heterogeneous local structure in single-cell RNA-seq data.
method Hierarchical sheaf spectral embedding (HSSE) framework.
result HSSE achieves competitive or improved performance in single-cell RNA-seq data representation learning.
The paper analyzes learning curves for kernel ridge regression with dot-product kernels.
problem Understanding the learning curves for different scaling regimes of data and model.
method Precise formulas for mean test error, bias, and variance in the mo∞ with m/dr constant regime. result A peak in the learning curve at m≈dr/r! for any integer r. Efficiently attacks large-scale graphs without using the whole graph.
problem Vulnerability of graph neural networks to adversarial attacks.
method Simplified Gradient-based Attack (SGA) method for large-scale graphs.
result SGA achieves significant time and memory efficiency improvements.
Workflow improves credit default prediction using machine learning.
problem Assessing creditworthiness and risk management in lending.
method Data preprocessing with Weight of Evidence, ensemble learning, and hyperparameter optimization.
result Enhanced accuracy in predicting credit default.
New method for scalable inference in large-scale regression models with complex error structures.
problem Challenges in statistical inference for large-scale regression models with dependent errors.
method Generalized Method of Wavelet Moments with Exogenous variables (GMWMX).
result Statistical validity and scalability of GMWMX for linear models with complex error structures.
Meta-learning predicts stock trading volumes by learning from each stock's unique patterns.
problem Predicting trading volumes for different stocks using a universal model.
method Dual-process meta-learning framework that learns common patterns with a meta-learner and specific patterns with stock-dependent parameters.
result Improves performance of various baseline models in volume predictions.
In the era of big data, practical applications in various domains continually generate large-scale time-series data. Among them, some data show significant or potential periodicity characteristics, such as meteorological and financial data. It is critical to efficiently identify the potential periodic patterns from mas…
This study examines how discretization improves neural forecasting models.
problem Improving predictive performance of neural forecasting models.
method Empirical investigation of data binning techniques on various neural forecasting architectures.
result Data binning almost always improves forecasting accuracy, but the type of binning is less important.
LSTM and gradient boosting models fail to outperform random chance in predicting MNQ futures.
problem Predicting intraday direction in MNQ futures using LSTM and gradient boosting.
method Comparing LSTM and gradient boosting models on 944 trading days of MNQ futures data.
result No model achieves statistically significant accuracy above random chance.
The study explains transformer scaling laws using statistical and approximation theories.
problem Understanding why transformer scaling laws exist for large models trained on low-dimensional data.
method Established statistical estimation and mathematical approximation theories for transformers on low-dimensional manifolds.
result Predicted a power law between generalization error and model and data sizes, with power depending on intrinsic data dimension.
Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution to the field of gait analysis, e.g., in increasing the classification performance. In order to ensure…
The paper investigates how irrelevant features affect clustering performance.
problem The challenge of identifying relevant features in unsupervised clustering tasks.
method Investigation of clustering performance with added irrelevant features.
result Different types of irrelevant features impact clustering outcomes differently.