This paper explains how model invariance improves generalization using data transformations.
problem Understanding why model invariance leads to better generalization performance.
method Introducing sample cover induced by transformations and refining generalization bounds.
result The sample covering number can be used to evaluate and select suitable data transformations.
Study proper sampling for X-ray transforms on simple surfaces.
problem Proper discretizing and sampling issues related to geodesic X-ray transforms on simple surfaces.
method Provide minimal sampling rates for faithful reconstruction, quantify sampling quality, and predict artifacts.
result Minimal sampling rates and artifact prediction for geodesic X-ray transforms on simple surfaces.
Improves MCMC performance with adaptive affine transformations.
problem Improving the performance of Markov Chain Monte Carlo samplers.
method Adaptive learning of bijective affine transformations during sampling.
result Adaptive affine transformations improve the quality of samples at low computational cost.
PPT optimizes transformer behavior by steering its latent posterior using prior samples.
problem Eliciting desired behavior from transformers without backpropagation.
method Posterior Prefix Tuning (PPT) uses predictive Monte Carlo (PMC) samples and importance sampling to optimize the latent posterior.
result PPT optimizes transformer behavior without backpropagation, achieving high utility across different utility functions.
Paper improves tensor completion by reducing sample entries needed.
problem Reducing the number of required sample entries for tensor completion.
method Utilizes multi-rank and unitary transformation in tensor singular value decomposition.
result Provides a bound on the number of required sample entries for tensor completion.
Accelerates TPP sampling with speculative decoding for faster sequence generation.
problem Efficiently sampling from complex temporal point processes.
method Adapting speculative decoding techniques from language models to TPPs.
result Achieves significant speedup (2-6x) while maintaining distributional accuracy.
Transformers can outperform feedforward and recurrent networks due to dynamic sparsity.
problem Understanding when and why Transformers outperform other neural network architectures.
method Analyzing a sequence-to-sequence data generating model with dynamic sparsity, proving sample complexity differences between feedforward, recurrent, and Transformers.
result Transformers can learn dynamic sparsity models with lower sample complexity than feedforward and recurrent networks.
Abstractor enhances Transformers for relational reasoning, improving sample efficiency and performance.
problem Improving sample efficiency and performance in relational tasks.
method Introduces Abstractor module with relational cross-attention to enable explicit relational reasoning.
result Dramatic improvements in sample efficiency and performance on various relational tasks.
CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.
problem Transformer sample inefficiency in simple tasks.
method Demonstrated through parity-learning setup, showing CoT reduces required samples from exponential to polynomial.
result Transformer learns function within polynomial samples with CoT, requiring exponential samples without CoT.
We propose a new class of transforms that we call {\it Lehmer Transform} which is motivated by the {\it Lehmer mean function}. The proposed {\it Lehmer transform} decomposes a function of a sample into their constituting statistical moments. Theoretical properties of the proposed transform are presented. This transform…
Framework learns to transform majority to minority samples for balanced classification.
problem Imbalanced classification leading to biased predictions.
method Minimizes MMD and uses triplet loss for global alignment and boundary awareness.
result Consistent improvements over classical and generative baselines in AUROC, G-mean, F1-score, and MCC.
Nested sampling improved for arbitrary priors.
problem Technical obstacle to using nested sampling with arbitrary priors.
method Parametric bijectors trained on samples from a desired prior density.
result Nested sampling can be used with arbitrary priors.
Time series forecasting with limited data is a challenging yet critical task. While transformers have achieved outstanding performances in time series forecasting, they often require many training samples due to the large number of trainable parameters. In this paper, we propose a training technique for transformers th…
This work explores test-time scaling strategies for LLMs, improving sample efficiency and expressiveness.
problem Understanding the sample efficiency and expressiveness of test-time scaling strategies for LLMs.
method Established separation and expressiveness results for self-consistency, best-of-n, and self-correction strategies. result Self-correction enables Transformers to simulate online learning over multiple tasks without prior knowledge.
Algorithm samples polygons of fixed edge lengths in any dimension.
problem Sampling random closed polygons with fixed edge lengths in any dimension.
method Weighted edge vectors on unit sphere, Möbius transformation, reweighting factors.
result Algorithm samples polygons according to standard probability measures efficiently.
New method detects symmetries beyond affine transformations.
problem Current methods limit symmetry detection to affine transformations.
method Framework for discovering continuous symmetry beyond affine transformations.
result Method is competitive for large sample sizes and superior for small sample sizes.
Transformers can learn optimal regression mixtures efficiently.
problem Limited adoption of tailored regression methods due to their model-specific nature.
method Constructed a generative process for a mixture of linear regressions and used transformers to learn optimal predictors.
result Transformers achieve low mean-squared error and make predictions close to the optimal procedure.
REST improves robustness of black-box models to geometric transformations.
problem Overconfident incorrect predictions on out-of-distribution samples.
method REinforcement Spatial Transform learner (REST) that transforms input data into in-distribution samples.
result Improves robustness to geometric transformations and sample efficiency.
Efficient algorithms find optimal monotone transforms for calibration under strictly convex losses.
problem Calibrating estimations to improve performance with monotone transforms.
method Proposed linear-time and space algorithm for finding optimal monotone transforms for specific loss functions. Also proposed an anytime algorithm with linear space and pseudo-linearithmic time complexity.
result Optimal monotone transforms are unique and can be found efficiently for various strictly convex loss functions.
Self-attention prefers sparse functions of input sequences, reducing sample complexity.
problem Understanding the inductive biases of self-attention in modeling long-range dependencies.
method Theoretical analysis and synthetic experiments to probe sample complexity of learning sparse functions with Transformers.
result Bounded-norm Transformer networks can represent sparse functions of the input sequence with logarithmic sample complexity.
Rough Transformers improve time series modeling with lower costs and better performance.
problem Inefficient modeling of irregularly sampled time series data.
method Signature patching for continuous-time representations, reducing computational costs.
result Rough Transformers outperform vanilla Transformers and Neural ODE models.
Distance-based tests, also called "energy statistics", are leading methods for two-sample and independence tests from the statistics community. Kernel-based tests, developed from "kernel mean embeddings", are leading methods for two-sample and independence tests from the machine learning community. A fixed-point transf…
DNFS trains efficient samplers for discrete distributions using locally equivariant Transformers.
problem Sampling from unnormalised discrete distributions.
method DNFS learns a rate matrix to satisfy the Kolmogorov equation, using control variates and locally equivariant Transformers.
result DNFS achieves efficient and effective sampling across various applications.
Method uses normalizing flows to efficiently sample from complex target densities.
problem Sampling from complex target densities with zero values in regions of transformation.
method Normalizing flows to address exploding reverse Kullback-Leibler divergence.
result Demonstrated efficient sampling from multi-mode complex density function.
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
Transformers capture combinatorial tasks with bounded error and logarithmic sample dependence.
problem Capturing complex combinatorial tasks with bounded error and sample efficiency.
method Formal definition of algorithmic capture, empirical analysis of infinite-width transformers, upper bounds on computational complexity.
result Transformers exhibit an inductive bias favoring simpler algorithmic procedures over higher complexity ones.
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.
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color transformations. Instead of using predefined transformations, our work learns data augmentati…
BoostTransformer uses boosting to improve transformer efficiency and accuracy.
problem Heavy computational resources and hyperparameter tuning in transformer architectures.
method Augments transformers with boosting principles through subgrid token selection and importance-weighted sampling, incorporating a least square boosting objective directly into the pipeline.
result BoostTransformer demonstrates faster convergence and higher accuracy compared to standard transformers.
This paper precisely estimates transformer derivatives for explicit learning guarantees.
problem Computing fully-explicit generalization bounds for transformers with precise higher-order derivative estimates.
method Analyzes and estimates all higher-order derivatives of transformers with multiple attention heads and layer normalization.
result Obtains explicit pathwise generalization bounds for transformers learning from non-i.i.d. samples.
New sampling method for heavy-tailed distributions using Langevin Algorithm.
problem Sampling from heavy-tailed distributions efficiently.
method Transformed Unadjusted Langevin Algorithm on specific transformations.
result Polynomial-order oracle complexities for certain heavy-tailed densities.
Enhanced decision-making through Dreamer's anticipatory trajectories and Online Decision Transformer.
problem Efficiently integrating world models with decision transformers.
method Combining Dreamer's trajectory forecasting with Online Decision Transformer's adaptive learning.
result Notable improvements in sample efficiency and reward maximization.
Efficiently transforms samples from various statistical models.
problem Approximately transforming samples from one statistical model to another without knowing the source model's parameters.
method Constructs computationally efficient procedures to reduce uniform, Erlang, and Laplace models to general target families.
result Establishes nonasymptotic reductions between canonical high-dimensional problems, such as mixtures of experts, phase retrieval, and signal denoising.
New sampling method using regularized Wasserstein proximal for Gibbs distributions.
problem Sampling from Gibbs distributions with numerical stability and efficiency.
method Preconditioned regularized Wasserstein proximal operator.
result Discrete-time convergence analysis and explicit bias characterization.
Optimizes reinforcement learning by prioritizing sets of samples over individual ones.
problem Limits exploration and improvement on harder examples due to focusing on isolated samples.
method Proposes Pass@K Policy Optimization (PKPO) to optimize for sets of samples that maximize reward when considered jointly.
result Optimization with novel low variance unbiased estimators for pass@k and its gradient leads to significant pass@k gains.
TTT improves transformer models for in-context learning.
problem Improving transformer models for efficient in-context learning.
method Gradient-based TTT method for linear transformers, with theoretical and empirical analysis.
result TTT significantly reduces the sample size required for in-context learning.
Algorithm learns affine transformations robustly from corrupted samples.
problem Learning affine transformations from corrupted samples.
method New geometric certificate and iterative improvement method.
result Total variation distance of O(ε) between learned and original distributions. 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.
New algorithm learns halfspaces with noise using Forster decomposition.
problem Learning halfspaces in noisy data.
method Forster decomposition and efficient mixture of distributions.
result First polynomial-time algorithm with strongly polynomial sample complexity.
Neural networks compress and sample WDN contamination dynamics efficiently.
problem Infrastructure monitoring of complex, networked systems like water distribution networks is expensive and challenging.
method Developed Graph Fourier Transform (GFT) operators and neural networks (NN) for efficient data collection and inference.
result High accuracy reconstruction of contamination dynamics using only 5-10% of the sample set.
Efficient algorithm finds fast Transformer models.
problem Slow inference time of Transformer models.
method Decompose Transformer architecture into components, use sampling-based one-shot search.
result Achieved 10% to 30% speedup on pre-trained BERT and 70% on top of a previous state-of-the-art model.
DGPFM uses deep Gaussian processes to map functions accurately and quantify uncertainty.
problem Learning mappings between functional spaces, especially when data are noisy, sparse, or irregularly sampled.
method Constructs a sequence of GP-based linear and nonlinear transformations directly in function space, leveraging kernel integral transforms, GP conditional means, and nonlinear activations sampled from Gaussian processes.
result Empirical results show DGPFM outperforms existing methods in predictive accuracy and uncertainty calibration.
The study finds conditions for compressing the hidden dimension of Graph Transformers for transductive learning.
problem The challenge of efficiently analyzing and training Graph Transformers for transductive learning.
method Theoretical bounds on hidden dimension compression for Graph Transformers, considering both sparse and dense variants.
result Theoretical findings on how and under what conditions the hidden dimension of Graph Transformers can be compressed.
This paper considers fair probabilistic binary classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints that are linear in conditional means of scores while minimizing a cross-entropy…
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transf…
A new method estimates rare events using tensor trains.
problem Estimating rare event probabilities in high-dimensional problems.
method Approximating optimal importance distribution via tensor-train decompositions and compositions.
result Better variance reduction and efficient computation of rare event probabilities.
Compressive sensing is an impressive approach for fast MRI. It aims at reconstructing MR image using only a few under-sampled data in k-space, enhancing the efficiency of the data acquisition. In this study, we propose to learn priors based on undecimated wavelet transform and an iterative image reconstruction algorith…
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.