The study sets lower bounds on MMSE for inferring sensitive features from noisy data.
problem Estimating sensitive features from noisy observations of correlated features.
method Adversarial evaluation framework based on MMSE estimation with theoretical lower bounds.
result Derives closed-form bounds for linear models, showing optimality in noise variance.
Recent studies in the literature have paid much attention to the sparsity in linear classification tasks. One motivation of imposing sparsity assumption on the linear discriminant direction is to rule out the noninformative features, making hardly contribution to the classification problem. Most of those work were focu…
ERM performs well in feature learning with minimal feature maps.
problem Empirical risk minimization in feature learning with square loss.
method Asymptotic and non-asymptotic analysis of ERM performance.
result Excess risk quantiles of ERM match those of oracle procedure under certain conditions.
Deep linear networks exhibit collapsing features and classifiers across datasets.
problem Understanding the collapse of features and classifiers in deep linear networks.
method Theoretical and empirical analysis of deep linear networks with MSE and CE losses.
result Deep linear networks exhibit NC properties, collapsing features and classifiers to orthogonal vectors.
New method for interpreting non-linear models using forward marginal effects.
problem Interpreting non-linear models' feature effects is challenging.
method Introducing forward marginal effects and partitioning feature space for better interpretation.
result Improved interpretation of non-linear prediction functions.
Study compares random and learned features in deep Bayesian linear models.
problem Understanding how feature learning affects generalization in deep learning.
method Comparing deep random feature models to deep networks with trained layers.
result Random feature models can display double-descent behavior, while deep networks do not.
RFM reduces feature space for linear models, improving sparse recovery.
problem Sparse linear regression and low-rank matrix recovery.
method Recursive Feature Machines (RFM) that alternates between reweighting feature vectors by AGOP and learning prediction function.
result RFM generalizes IRLS and outperforms deep linear networks.
New algorithm disentangles latent features without strict assumptions.
problem Disentangling complex data-generating mechanisms into causally interpretable latent features.
method Linear CRL algorithm with topological ordering, pruning, and disentanglement.
result Recovering latent causal features up to an equivalence class under weaker assumptions.
Two new algorithms reduce feature space while preserving non-linear relationships.
problem High-dimensional data and overfitting issues.
method Bias-variance analysis for non-linear transformations and generalized linear models.
result Competitive performance on regression and classification tasks.
Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features …
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.
New framework allows reinforcement learning with polynomial sample complexity.
problem Generalization in reinforcement learning with function approximation.
method Introduces Bilinear Classes, a structural framework for RL.
result Polynomial sample complexity for Bilinear Classes, matching best known bounds.
Supervised dimensionality reduction has emerged as an important theme in the last decade. Despite the plethora of models and formulations, there is a lack of a simple model which aims to project the set of patterns into a space defined by the classes (or categories). To this end, we set up a model in which each class i…
In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification. The proposed method iteratively transforms the data from the original feature space of each modality to a new common feature space along with finding a joint compact descriptio…
Deconfounding scores improve causal effect estimation with weak overlap.
problem Challenges in causal treatment effect estimation due to weak overlap in high-dimensional data.
method Propose deconfounding scores to preserve identification and target estimation while improving overlap.
result Prognostic scores are overlap-optimal under a broad family of generalized linear models with Gaussian features.
New algorithms for model selection in linear contextual bandits without feature diversity conditions.
problem Model selection in linear contextual bandits without feature diversity conditions.
method Data-adaptive algorithms that provide model selection guarantees without feature diversity conditions.
result O(d^α T^{1-α}) model selection guarantees with no feature diversity conditions.
The nearest-centroid classifier is a simple linear-time classifier based on computing the centroids of the data classes in the training phase, and then assigning a new datum to the class corresponding to its nearest centroid. Thanks to its very low computational cost, the nearest-centroid classifier is still widely use…
LDA improves image classification accuracy with fewer features.
problem Fine-grained image classification with pretrained features.
method Supervised dimensionality reduction with LDA before linear probing.
result LDA improves accuracy over full features in 11 out of 12 configurations.
Wide neural networks converge linearly to zero loss with feature learning.
problem Optimizing wide neural networks with feature learning guarantees.
method Gradient flow analysis for wide shallow and multi-layer NNs.
result Training loss converges linearly to zero for wide NNs under GF, demonstrating feature learning and better generalization.
We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables memory-limited execution of several statistical analyses over streams, including online featu…
This note considers softmax parameter estimation when little/no labeled training data is available, but a priori information about the relative geometry of class label log-odds boundaries is available. It is shown that `data-free' softmax model synthesis corresponds to solving a linear system of parameter equations, wh…
LLT-ECG classifies ECG signals without backpropagation using linear laws.
problem ECG signal classification efficiency and verifiability.
method Forward linear law identification for ECG signal features.
result State-of-the-art performance on real-world ECG datasets.
SQFA learns features maximizing Fisher-Rao distance for better classification.
problem Improving classification accuracy through feature learning.
method SQFA learns linear features maximizing Fisher-Rao distance between class-conditional distributions.
result SQFA-H features achieve the best classification accuracy.
The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of deep feature extraction and non-linear feature representation, the clustering algorithm based on deep learning has become a hot research topic in the field of hyperspectral remote s…
This paper uses MIO to select features for kernel SVM classification.
problem Feature selection for kernel SVM classification.
method Mixed-integer optimization (MIO) for feature subset selection.
result The MIO approach can often outperform linear-SVM-based methods in prediction performance.
New RL method learns to skip states in linearly qπ-realizable MDPs, simplifying to linear MDPs.
problem Online RL in episodic MDPs with linearly qπ-realizable action-values. method Derives a novel algorithm that learns to skip states and applies a linear MDP algorithm.
result First polynomial-sample-complexity online RL algorithm for linearly qπ-realizable MDPs. Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets they do not take full advantage of the extra data due to their linear nature, and typically underfit. We propose a new class of models which …
Identifying small subsets of features that are relevant for prediction and/or classification tasks is a central problem in machine learning and statistics. The feature selection task is especially important, and computationally difficult, for modern datasets where the number of features can be comparable to, or even ex…
Objective: A variety of pattern analysis techniques for model training in brain interfaces exploit neural feature dimensionality reduction based on feature ranking and selection heuristics. In the light of broad evidence demonstrating the potential sub-optimality of ranking based feature selection by any criterion, we …
Paper proposes a new method to optimize feature coordinates for better image classification.
problem Improving feature extraction for better machine learning classification.
method Mutual-energy inner product optimization method.
result The method enhances low-frequency features and suppresses high-frequency noise, leading to better classification results.
Signature portfolios approximate optimal wealth in non-Markovian markets.
problem Approximating optimal wealth in non-Markovian markets.
method Linear path-functional portfolios based on signatures of market weights.
result Signature portfolios can uniformly approximate any continuous portfolio function.
The paper analyzes how overparameterized models can generalize well in multiclass classification.
problem Generalization in multiclass classification with overparameterized models.
method Survival/contamination analysis framework adapted for multiclass classification.
result Multiclass classification can generalize well even with many classes, unlike regression tasks.
We present a method to stop the evaluation of a prediction process when the result of the full evaluation is obvious. This trait is highly desirable in prediction tasks where a predictor evaluates all its features for every example in large datasets. We observe that some examples are easier to classify than others, a p…
Representing examples in a way that is compatible with the underlying classifier can greatly enhance the performance of a learning system. In this paper we investigate scalable techniques for inducing discriminative features by taking advantage of simple second order structure in the data. We focus on multiclass classi…
CFA improves model's ability to generalize across unseen domain-class combinations.
problem Challenges in real-world machine learning applications due to data distribution shifts and limited training data.
method Developed Compositional Feature Alignment (CFA) technique to improve CG ability of pretrained models.
result CFA outperforms common finetuning techniques in compositional generalization.
Regularization effect found in neural feature alignment.
problem Implicit regularization in deep learning models.
method Geometrical viewpoint and analysis of Rademacher complexity.
result Neural features align along task-relevant directions, leading to regularization.
Algorithm captures and refines features for efficient lifelong learning.
problem Efficiently learning multiple tasks sequentially with limited data.
method Proposes a lifelong learning algorithm that maintains and refines internal feature representation.
result Proves sample complexity improvement and matches lower bound for efficiency.
In this paper, a genetic algorithm-based frequency-domain feature search (GAFDS) method is proposed for the electroencephalogram (EEG) analysis of epilepsy. In this method, frequency-domain features are first searched and then combined with nonlinear features. Subsequently, these features are selected and optimized to …
New models improve machine learning accuracy and transparency in finance.
problem Black-box machine learning models lack interpretability in regulated industries.
method Introducing generalized groves of neural additive models with clear feature categories and interactions.
result Generalized groves of neural additive models achieve high accuracy with predominantly linear and sparse nonlinear components.
Proposes a new scoring function for linear classifiers to improve object positioning in feature space.
problem Lack of information about relative positions of recognized objects in feature space.
method Calculates a scoring function based on object distance from decision boundary and class centroid.
result Demonstrates effectiveness of the proposed method compared to other ensemble algorithms on multiple datasets.
Wide neural networks with weight decay exhibit neural collapse.
problem Proving neural collapse in wide neural networks trained with weight decay.
method Generic guarantees on neural collapse for wide networks with weight decay, proving low training error and balancedness, and bounded conditioning.
result First proof of neural collapse in end-to-end training of wide neural networks with weight decay.
We present the Parallel, Forward-Backward with Pruning (PFBP) algorithm for feature selection (FS) in Big Data settings (high dimensionality and/or sample size). To tackle the challenges of Big Data FS PFBP partitions the data matrix both in terms of rows (samples, training examples) as well as columns (features). By e…
Develops efficient method for updating models with small data changes.
problem Efficiently updating models when data changes (e.g., adding/removing instances/features).
method Generalized Low-Rank Update (GLRU) for non-linear estimators.
result Provides updated solutions with computational complexity proportional to dataset changes.
New method deconfounds deep learning feature representations using counterfactual approach.
problem Improving model stability in deep learning models under dataset shifts.
method Adopting last layer features of DNNs trained with softmax activation for logistic regression, and applying counterfactual deconfounding.
result Counterfactual deconfounding can be applied to DNN feature representations, improving model stability.
New tree and forest methods use oblique splits for better risk bounds.
problem Improving risk bounds for regression algorithms.
method Randomized decision trees and forests with oblique splits.
result Oblique splits lead to better risk bounds for multi-index models.
SnapBoost uses random base hypothesis classes to improve gradient boosting performance.
problem Improving gradient boosting performance.
method Heterogeneous Newton Boosting Machine (HNBM) with variable base hypothesis classes.
result SnapBoost achieves better generalization loss than competing frameworks.
New approach selects sparse features without validation.
problem Overfitting and high storage/compute costs in AI models.
method Phase transition in probability of feature retrieval.
result Flexible approach for various models and loss functions.
This manuscript studies statistical properties of linear classifiers obtained through minimization of an unregularized convex risk over a finite sample. Although the results are explicitly finite-dimensional, inputs may be passed through feature maps; in this way, in addition to treating the consistency of logistic reg…