We find a deterministic equivalent for random feature regression's test error, independent of feature map dimension.
problem Understanding the generalization performance of random feature ridge regression.
method We derive a deterministic equivalent for the test error of RFRR under a concentration property, showing it can be approximated by a closed-form expression dependent on feature map eigenvalues.
result Our approximation guarantee is non-asymptotic, multiplicative, and independent of the feature map dimension, providing a tight result for the smallest number of features achieving optimal minimax error rate.
A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Featu…
Study shows how feature weighting affects neural network regularization.
problem Understanding how feature weighting influences neural network regularization.
method Derived equivalence paths connecting different weighting matrices and ridge regularization levels.
result Ridge estimators trained on weighted features are asymptotically equivalent when evaluated against test vectors.
Two statistical tasks are shown to have equivalent sample complexity.
problem Determining if a function depends on only a few variables and identifying those variables.
method Proved statistical equivalence of feature selection and junta testing through sample complexity analysis.
result Brute-force algorithm is sample-optimal for both tasks with optimal sample size.
The statistically equivalent signature (SES) algorithm is a method for feature selection inspired by the principles of constrained-based learning of Bayesian Networks. Most of the currently available feature-selection methods return only a single subset of features, supposedly the one with the highest predictive power.…
Gaussian equivalence fails for simple polynomial embeddings in quadratic scaling RF models.
problem Failure of Gaussian equivalence in polynomial feature embeddings under quadratic scaling.
method Introduced Conditional Gaussian Equivalent (CGE) model to capture non-Gaussian behavior.
result Correct asymptotics derived for training and test errors in CGE model.
We discuss theoretical aspects of the product rule for classification problems in supervised machine learning for the case of combining classifiers. We show that (1) the product rule arises from the MAP classifier supposing equivalent priors and conditional independence given a class; (2) under some conditions, the pro…
New equivalences found between subsampling and ridge regularization methods.
problem Establishing precise structural and risk equivalences between subsampling and ridge regularization.
method Proved structural and risk equivalences between subsample ridge estimators and different ridge regularization levels and subsample aspect ratios.
result Optimally tuned ridge regression exhibits a monotonic prediction risk in the data aspect ratio.
We prove that the criterion for Markov equivalence provided by Zhao et al. (2005) may involve a set of features of a graph that is exponential in the number of vertices.
Study of eigenvalues in nonlinear kernels for classification of separable data.
problem Understanding the applicability of linear equivalents in nonlinearly separable data classification.
method Analysis of conjugate kernels and their quadratic equivalents for a canonical nonlinearly separable dataset (XOR problem).
result Identification of regimes where nonlinear kernels deviate from linear equivalents, leading to label-aligned eigenspaces.
New insights into pseudo-Anosov flows with special periodic orbits.
problem Understanding pseudo-Anosov flows with periodic orbits in 3-manifolds.
method Analyzing the topological features corresponding to trees of scalloped regions and classifying flows with the same free homotopy data.
result Explicit examples of flows with the same free homotopy data but not orbit equivalent.
Random matrix theory explains how neural networks adapt to data.
problem Understanding how neural networks learn and generalize from data.
method Random matrix analysis of two-layer neural networks.
result Sharp characterization of feature spectrum and generalization error.
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.
The study examines markets with multiple numéraires and finds equivalent martingale measures.
problem Analyzing markets with diverse assets and numéraires.
method Theoretical foundations and results on superreplication prices.
result Existence of equivalent martingale measures in markets with multiple numéraires.
Tangle machines are topologically inspired diagrammatic models. Their novel feature is their natural notion of equivalence. Equivalent tangle machines may differ locally, but globally they are considered to share the same information content. The goal of tangle machine equivalence is to provide a context-independent me…
Latent feature models (LFM)s are widely employed for extracting latent structures of data. While offering high, parameter estimation is difficult with LFMs because of the combinational nature of latent features, and non-identifiability is a particularly difficult problem when parameter estimation is not unique and ther…
Optimized nonlinearities enhance generalization in random feature models.
problem Improving generalization performance in random feature models.
method Analyzed and defined optimal nonlinearities from Gaussian model parameters.
result Optimized nonlinearities achieve better generalization performance than ReLU.
Unified derivation of high-dimensional linear models using stochastic gradient descent.
problem Performance analysis of high-dimensional linear models trained with stochastic gradient descent.
method Derivation of a deterministic equivalence for the two-point function of a random matrix resolvent.
result Unified understanding of model performance including previously known and novel results.
The paper analyzes ridge regression with random features for non-identically distributed data.
problem Analyzing ridge regression performance for data with heterogeneous variance profiles.
method Combining linear-plus-chaos approximation and operator-valued free probability.
result Derives asymptotic equivalents for training and test risks under non-identically distributed data.
An algorithm preserves topological features in dimensionality reduction.
problem Preserving topological features in dimensionality reduction.
method Simulated annealing for finding a linear projection preserving persistent homology.
result Measures of topological equivalence between filtrations.
Deep random feature models are analyzed for their performance with exact asymptotic expressions.
problem Understanding the performance of deep random feature models.
method Established a novel universality result and used the convex Gaussian Min-Max theorem.
result Exact asymptotic expressions for the performance of deep random feature models are derived.
Deep networks learn hierarchical data by invariant representations.
problem How many examples are needed for deep networks to learn hierarchical data?
method Random Hierarchy Model: synthetic tasks inspired by language and images hierarchy.
result Deep networks learn by invariant representations and require a detectable number of correlations between low-level features and classes.
PS-IG improves feature attribution by reducing noise and variance.
problem Improving feature attribution in machine learning models.
method Path-sampled integrated gradients (PS-IG) computes expected value over sampled baselines.
result PS-IG reduces attribution variance by a factor of 1/3 under uniform sampling.
The paper matches features in images using centro-affine invariants and heat flow.
problem Feature matching in images with invariant algorithms.
method Developed an invariant algorithm using centro-affine invariants and heat flow.
result The algorithm compares favorably with existing feature matching methods.
The study proves Gaussian universality of deep random features learning.
problem Understanding the test error in deep random features learning.
method Proving Gaussian universality of test error in ridge regression and arbitrary convex losses.
result Sharp asymptotic formula for test error in ridge regression setting.
Researchers discover all affinely homogeneous models for surfaces in 4D space.
problem Identifying all affinely homogeneous models for surfaces in 4D space.
method Improved power series method of equivalence, capturing invariants at the origin, creating branches, and infinitesimalizing calculations.
result Find several inequivalent terminal branches yielding each to some nonempty moduli space of homogeneous models.
Deep neural networks favor symmetric structures, enabling multilevel symmetries.
problem Understanding and optimizing deep neural networks.
method Formulating DNN training as convex Lasso problems with geometric algebra.
result Deep networks inherently favor symmetric structures, enabling multilevel symmetries.
This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features under certain conditions, the network feature naturally has the rotation-equivariance property. Rota…
Deep neural nets on 1-D data are convex Lasso models with reflection features.
problem Training neural networks on 1-D data.
method Proving equivalence to convex Lasso problems with discrete, explicitly defined dictionary matrices.
result Reflection features in neural networks with certain activations.
We consider the applications of the Frank-Wolfe (FW) algorithm for Apprenticeship Learning (AL). In this setting, we are given a Markov Decision Process (MDP) without an explicit reward function. Instead, we observe an expert that acts according to some policy, and the goal is to find a policy whose feature expectation…
Supporting evidence for adaptive feature program across diverse models.
problem Analyzing feature learning in neural networks.
method Over-parameterized sequence models and feature error measure (FEM).
result FEM is decreasing during training of adaptive feature models.
Unified framework for fairness, robustness, and distribution shifts.
problem Diverse failure modes of machine learning systems.
method Formalizes biases as violations of conditional independence and proves equivalence conditions.
result Equivalent effects of biases in different failure modes under specific conditions.
Feature selection has been proven a powerful preprocessing step for high-dimensional data analysis. However, most state-of-the-art methods tend to overlook the structural correlation information between pairwise samples, which may encapsulate useful information for refining the performance of feature selection. Moreove…
This research simplifies computation of feature attribution methods under certain conditions.
problem Computational complexity of feature attribution methods, especially power indices.
method Identifying conditions for polynomial computation and introducing new indices.
result Conditions for efficient computation of feature attribution methods are identified.
Improved convergence in deep learning networks via gradient transformation.
problem Reduced convergence speed in deep learning networks.
method Gradient transformation to weight gradients and recursive condition number reduction.
result Improved convergence speed and accuracy in image classification tasks.
Featurization improves density ratio estimation for complex data.
problem Difficulty in estimating density ratios for high-dimensional, different distributions.
method Invertible generative model to map distributions into a common feature space.
result Improved accuracy in density ratio estimation through feature space.
New random feature maps for Laplacian and related kernels.
problem Challenges in approximating the Laplacian kernel and its generalizations.
method Developed random feature maps for Laplacian and related kernels, providing efficient sampling schemes.
result Demonstrated the efficacy of these random feature maps on real datasets.
We analyze in this paper a random feature map based on a theory of invariance I-theory introduced recently. More specifically, a group invariant signal signature is obtained through cumulative distributions of group transformed random projections. Our analysis bridges invariant feature learning with kernel methods, as …
A new feature selection method using attention for neural networks.
problem Feature selection for neural networks with a budget constraint.
method Sequential Attention: greedy forward selection with attention weights.
result Achieves state-of-the-art results for neural networks.
Solves double coset problem for braid group H_n.
problem Double coset problem in braid group B_n modulo H_n.
method Uses Garside's decomposition of braids in B_n.
result Demonstrates stable equivalence of Link Problem to solvable algebraic problem.
A fast feature selection method using OLS and SOCC for classification.
problem Feature selection for linear classification.
method Orthogonal Least Squares (OLS) with Squared Orthogonal Correlation Coefficient (SOCC).
result The proposed method outperforms other feature selection methods in speed and accuracy.
Study extends bounds on sample covariance matrices with general dependence.
problem Quantitative bounds on sample covariance matrices with i.i.d. columns.
method Extends previous work on deterministic equivalent to rectangular random matrices with general dependence structure.
result Proves quantitative bounds involving dimensions and spectral parameter, including closer proximity to real positive semi-line.
Deep neural networks and Gaussian processes are shown to be equivalent through activation functions.
problem Understanding the relationship between neural networks and Gaussian processes.
method Developing an equivalence theory based on activation functions and kernels.
result Models can be seen as neural networks with improved uncertainty prediction or deep Gaussian processes with increased accuracy.
FFCP improves FCP's speed without sacrificing accuracy.
problem Inefficient feature transformation in FCP.
method Introduces FFCP using Taylor expansion for faster computation.
result FFCP achieves a 50x speedup with comparable accuracy.
A novel feature selection method for SVM improves model accuracy and interpretability.
problem Feature selection in nonlinear SVM classification problems.
method Embedded min-max optimization problem, leveraging duality theory.
result Improves model accuracy and interpretability on benchmark data sets.
SAEs struggle with feature consistency across runs, hindering MI reliability.
problem Inconsistency of learned SAE features across different training runs.
method Propose using the Pairwise Dictionary Mean Correlation Coefficient (PW-MCC) to measure feature consistency.
result High levels of feature consistency (0.80 for TopK SAEs on LLM activations) are achievable with appropriate architectural choices.
Efficient algorithms for clustered Lasso and OSCAR reduce computational costs.
problem High dimensional regression with feature clustering.
method Efficient path algorithms for clustered Lasso and OSCAR, reducing computational costs.
result Proposed algorithms are more efficient than existing methods in numerical experiments.
SAFLe solves federated learning's trade-off between non-linearity and scalability.
problem Federated Learning's high communication overhead and performance collapse on non-IID data.
method SAFLe introduces a structured head of bucketed features and sparse, grouped embeddings, mathematically equivalent to a high-dimensional linear regression.
result SAFLe achieves a new state-of-the-art in analytic FL, outperforming linear AFL and multi-round DeepAFL.