Efficient privacy-preserving machine learning framework using random transformations.
problem Slow training and inference speed in privacy-preserving machine learning systems.
method Random transformations like linear and permutation, combined with arithmetic sharing.
result High efficiency and low computation cost in private machine learning.
New network learns non-parametric invariances from data.
problem Modeling non-parametric invariances in data.
method Introduces PRC-NPTN networks with permanent random connectomes.
result Improves generalization and outperforms existing methods.
Improved unsupervised anomaly detection using Random Forest.
problem Enhancing unsupervised anomaly detection accuracy.
method Training Random Forest to distinguish real and synthetic data, then applying transformed distances.
result Significant improvement in anomaly detection accuracy compared to other methods.
Random forest models systematically bias predictions; a numerical transform corrects this.
problem Systematic bias in random forest regression predictions.
method Defined a numerical transformation using training data to correct bias.
result Improved predictions across real-world and synthetic datasets.
Improved SRHT for linear SVM classification with higher accuracy.
problem Inefficient random projection methods for high-dimensional data.
method Importance sampling and deterministic top-r sampling for effective low-dimensional embedding. result Higher classification accuracy on real-life datasets.
Transformers learn random walks optimally with gradient descent.
problem Transformer interpretability and learning random walks.
method Theoretical analysis and gradient descent training.
result Transformers can predict random walks optimally with gradient descent.
The study examines lower and upper bounds of Wasserstein distances for affine transformations of random vectors.
problem Understanding Wasserstein distances for affine transformations of random vectors.
method Lower and upper bounds for affine transformations of random vectors in Rn are derived using Bures metric and compositions of affine maps. result Concrete lower bounds and upper bounds for affine transformations are derived and applied to various distributions.
GOAD improves anomaly detection across various data types.
problem Finding anomalies in diverse data types.
method GOAD combines classification and transformation-based methods.
result GOAD achieves state-of-the-art accuracy on multiple datasets.
Transforms random forests into efficient neural networks using imitation learning.
problem Inefficient architectures of existing methods for transforming random forests into neural networks.
method Generates training data from a random forest and learns a neural network to imitate its behavior.
result Implicit transformation creates efficient neural networks with better generalization.
Transformers can predict pseudo-random sequences from LCGs with unseen parameters and moduli.
problem Learning pseudo-random number sequences from linear congruential generators with unknown parameters and moduli.
method Investigated the ability of Transformers to learn LCG sequences with varying complexity and moduli. Analyzed embedding layers and attention patterns.
result Transformers can predict pseudo-random sequences from LCGs with unseen parameters and moduli, up to mexttest=216, using a two-step strategy. New technique improves time series forecasting with less data.
problem Challenges in time series forecasting with limited data.
method Random sampling of non-consecutive time steps to increase training samples and capture finer temporal dependencies.
result Competitive results achieved compared to state-of-the-art on real-world datasets.
The paper improves the robustness of approximate randomization tests.
problem Noisy data limits the robustness of approximate randomization tests.
method Derives non-asymptotic bounds and novel conditions for approximate randomization tests.
result Valid approximate randomization tests under data invariances can be derived.
A new method for graph-structured data improves transformer performance by incorporating topology.
problem Improving transformer performance on graph-structured data.
method Parameterizing topological masks as a learnable function of a weighted adjacency matrix, approximated with graph random features.
result Efficient masking algorithms provide strong performance gains for tasks on image and point cloud data.
Improves detection of low-rank signals from noisy data matrices.
problem Statistical detection of low-rank signals in noisy data matrices.
method Entrywise pre-transforming data matrix for non-Gaussian noise, sharp phase transition thresholds, central limit theorem for linear spectral statistics, hypothesis test.
result Improves detection of low-rank signals from noisy data matrices, generalizing known results.
Mixup improves model accuracy and calibration through data transformation and random perturbation.
problem Improving model accuracy and calibration in machine learning.
method Interprets Mixup as empirical risk minimization with data transformation and random perturbation.
result Mixup induces multiple known regularization schemes that prevent overfitting and overconfident predictions.
MLDL preserves manifold geometry in vector transformations.
problem Geometric deterioration in neural network transformations.
method Locally isometric smoothness (LIS) and Markov random field (MRF) encoding.
result Enhanced vector transformations into well-behaved metric homeomorphisms.
Study reveals neural scaling laws in random graphs and natural language models.
problem Understanding the origin of neural scaling laws in complex systems.
method Examined scaling laws in transformers trained on random walks and simplified natural language models.
result Neural scaling laws emerge in the absence of power law structure in data correlations.
Computation of moments of transformed random variables is a problem appearing in many engineering applications. The current methods for moment transformation are mostly based on the classical quadrature rules which cannot account for the approximation errors. Our aim is to design a method for moment transformation for …
Study excess risk in statistical inference with transformations.
problem Excess risk in estimating random variables from feature vectors and transformations.
method Characterize lossless transformations, develop test statistics, and information-theoretic bounds.
result Strongly consistent partitioning test statistic for lossless transformations.
Study investigates ruin probability with random premiums and risky investments.
problem Ruin probability with random premiums and risky investments.
method Laplace transform applied to a model with geometric Brownian motion.
result Asymptotic behavior of ruin probability for large initial capital values.
Random Transformers behave like polynomial models in ICL with asymptotic growth.
problem Understanding in-context learning capabilities of pretrained Transformers.
method Asymptotic analysis of a random Transformer with a fixed first layer and a trained second layer, considering growth in context length, input dimension, hidden dimension, and training parameters.
result The random Transformer's ICL error is equivalent to a finite-degree Hermite polynomial model.
New method calculates tail probabilities of random vectors under linear transformations.
problem Computing tail probabilities of random vectors under linear transformations.
method Characterization of regular variation on cones in [0,∞)d under random linear transformations. result Allows computation of probabilities of tail events that were previously negligible.
New method certifies images against transformations like rotations and translations.
problem Certifying robustness of images against transformations like rotations and translations.
method Randomized smoothing with three different kinds of defenses.
result Individual certificates can be obtained via statistical error bounds or efficient online inverse computation.
A new decision tree variant improves linear model performance.
problem Improving decision tree performance on non-linear data.
method Extremely random tree with non-linear data transformation and linear observer.
result Outperforms linear models on benchmark dataset.
New method augments data for segmentation tasks using generative models.
problem Limited annotated data for deep learning segmentation.
method Task-driven data augmentation with generative models modeling deformation fields and intensity.
result Significantly outperforms conventional augmentation techniques in segmentation tasks.
Transformers learn to adapt to different task difficulties and resist distribution shifts.
problem Understanding and optimizing a Transformer's performance across various task difficulties and distribution shifts.
method Analyzing a pretrained Transformer on a mixture distribution of tasks, proving optimal convergence rates.
result Transformers achieve optimal convergence rates on tasks of specific difficulty levels, robust to distribution shifts.
HRFs adaptively linearize kernels for accurate approximations.
problem Linearizing softmax and Gaussian kernels for machine learning applications.
method Generalizes Bochner's Theorem for kernels, uses random features for compositional kernels.
result Strong theoretical guarantees and unbiased approximation with smaller relative errors.
We have applied a little-known data transformation to subsets of the Surveillance, Epidemiology, and End Results (SEER) publically available data of the National Cancer Institute (NCI) to make it suitable input to standard machine learning classifiers. This transformation properly treats the right-censored data in the …
Transforms offline algorithms to online with low regret in random order model.
problem Developing online algorithms with low approximate regret from offline approximation algorithms.
method General reduction theorem and coreset construction method.
result Achieves polylogarithmic ε-approximate regret for various online problems.
Study linear transformations' effects on data augmentation for improved estimation.
problem Improving performance in image and text classification tasks.
method Examined a family of linear transformations in over-parametrized linear regression settings.
result Transformations that preserve labels or mix data can improve estimation.
SRHM explains deep learning's hierarchy and insensitivity to transformations.
problem Understanding how deep networks learn hierarchical and invariant representations.
method Introducing sparsity to generative hierarchical models of data.
result Hierarchical representations and insensitivity to transformations correlate strongly with deep network performance.
Transformers trained on random classification tasks generalize well and can overfit without error.
problem Understanding how transformers generalize and overfit in-context.
method Analysis of implicit regularization during gradient descent training.
result Transformers can overfit without error and still generalize well.
Transformers exhibit sparse activation maps, reducing computational load and improving robustness.
problem Sparse activation in Transformer models.
method Extensive experiments on various Transformer architectures and tasks.
result Sparsity in Transformers is a prevalent phenomenon, reducing FLOP count and improving model robustness.
In earlier work we introduced geometrically natural probability measures on the group of all Möbius transformations in order to study "random" groups of Möbius transformations, random surfaces, and in particular random two-generator groups, that is groups where the generators are selected randomly, with a view to estim…
Gaussianization flows transform any random vector into a Gaussian, enabling efficient computation and sample generation.
problem Transforming any random vector into a Gaussian for efficient computation and sample generation.
method Iterative Gaussianization and normalizing flow model.
result Gaussianization flows are universal approximators and achieve better performance on tabular datasets.
Randomly initialized transformers show extreme token preferences.
problem Structural biases in randomly initialized transformers.
method Dissection of transformer architecture at initialization.
result Initialization-induced biases persist throughout training.
New algorithms update dynamic graph regression faster than existing methods.
problem Efficiently updating linear regression solutions for dynamic graphs.
method Subsampled randomized Hadamard transform and CountSketch.
result First sublinear update time randomized algorithms for dynamic graph regression.
Modeling functional data, this study uncovers the size-and-shape of functions under noisy observations.
problem Uncertainty in recovering a fixed effect function from noisy observations.
method Bayesian functional mixed model with priors on unitary transformations.
result It is possible to recover the size-and-shape of a square-integrable function μ. Transformers learn linear models in-context without updates.
problem Understanding how transformers mimic linear models in-context.
method Gradient flow on linear regression tasks with random initialization.
result Transformers achieve prediction error competitive with best linear predictors.
Tensorized Rademacher projections outperform Gaussian projections in reducing tensor dimensions.
problem Reducing the dimension of high-dimensional tensors for machine learning.
method Tensorized Rademacher random projections using Tensor Train decomposition.
result Tensorized Rademacher projections can replace Gaussian projections in tensor compression.
New methods reduce computational cost for Gaussian Markov Random Fields with sparse constraints.
problem Inference and simulation of GMRFs are computationally prohibitive with many constraints.
method Proposes a basis transformation into blocks of constrained and non-constrained subspaces.
result Significantly outperforms existing alternatives in computational cost.
Transformers learn to recall with non-orthogonal embeddings in realistic settings.
problem Understanding how transformers store and retrieve knowledge in practical scenarios.
method Analyzing a single-layer transformer with random embeddings trained on a token-retrieval task.
result Explicit formulas for the model's storage capacity reveal a multiplicative dependence on sample size, embedding dimension, and sequence length.
This paper proposes a deep learning model combining CNN and Transformer for improved credit default prediction.
problem Traditional machine learning models struggle with complex financial data and risk patterns.
method Combines CNN for local feature extraction and Transformer for global dependency modeling.
result The CNN+Transformer model outperforms traditional models in accuracy, AUC, and KS value.
Unified framework TSS certifies robustness against semantic transformations.
problem Certifying robustness of ML models against semantic transformations.
method Unified framework TSS categorizes transformations into resolvable and differentially resolvable, proposing randomized smoothing and stratified sampling strategies.
result Significantly outperforms state of the art on over ten types of semantic transformations.
Two new methods for analyzing repeated measures data using embeddings into Reproducing Kernel Hilbert Spaces.
problem Analyzing complex data structures with multiple features over time.
method Two generalizations of canonical correlation analysis for repeated measures data using embeddings into Reproducing Kernel Hilbert Spaces.
result Consistency rates for transformation and correlation estimators, relaxing common assumptions.
Paper argues for using functional theory of randomness for better understanding of data exchangeability and conformal prediction.
problem Understanding relationships between IID data assumptions and data exchangeability.
method Translation of conformal prediction results into the language of functional theory of randomness.
result Every confidence predictor valid for IID data can be transformed to a conformal predictor without losing much predictive efficiency.
Paper introduces graph-based transforms for video compression.
problem Efficiently represent video signals for compression.
method Develops two techniques for designing graph-based transforms (GL-GBTs and EA-GBTs).
result Graph-based transforms outperform traditional KLT in video compression.
New RFs reduce kernel approximation variance and improve Transformer performance.
problem Efficient approximation of Gaussian and softmax kernels for kernel methods and Transformers.
method Parameterized, positive, non-trigonometric RFs optimized for variance reduction.
result Significant variance reduction in practice, outperforming previous methods.