Random feature models can outperform a weak teacher with early stopping.
problem Generalization from a weak to a strong model in random feature networks.
method Random feature models, early stopping, proving weak-to-strong generalization.
result Random feature models can outperform a weak teacher with early stopping.
Bayesian priors improve neural network performance on weak signals.
problem Challenges in encoding domain knowledge for weak signals in neural networks.
method Proposed a new joint prior over local scale parameters for feature sparsity and signal-to-noise ratio, optimized with Stein gradient.
result Improved prediction accuracy on various datasets, including genetics applications with weak and sparse signals.
Large learning rates cause oscillations in NN weights that improve generalization.
problem Improving generalization of neural networks trained with large learning rates.
method Theoretical analysis and feature-noise data generation model.
result Oscillating SGD with large learning rates benefits NN generalization by effectively learning weak features.
A new method for weakly supervised learning that improves model accuracy.
problem Training machine learning models with precise labels is expensive; weak supervision provides a low-cost alternative.
method Data consistent weak supervision algorithm that searches over classifiers to find plausible labelings, considering features of the training data and estimating labels for low/no coverage data.
result Empirically, the method significantly outperforms state-of-the-art weak supervision methods on text and image classification tasks.
Study shows how a strong model can learn a task's feature while retaining other capabilities.
problem How to align superhuman AI systems using weak-to-strong generalization.
method Two-layer neural networks, reward-model learning, multi-step SGD, feature learning.
result The strong model efficiently learns task features while retaining general capabilities.
A powerful network teaches a weak one, improving its performance.
problem Improving the performance of a weak neural network using a more powerful one.
method During training, a weak network learns features from a strong network to minimize feature distance.
result A weak neural network can increase its performance by learning from a more powerful network.
Paper analyzes weak-to-strong generalization in CNNs, identifying data-scarce and data-abundant regimes.
problem Weak-to-strong generalization in CNNs trained on weak models.
method Formal analysis of gradient descent dynamics in data-scarce and data-abundant regimes.
result Identifies two regimes and distinct mechanisms of generalization in each.
We recall the Chernoff-Marsden definition of weak symplectic structure and give a rigorous treatment of the functional analysis and geometry of weak symplectic Banach spaces. We define the Maslov index of a continuous path of Fredholm pairs of Lagrangian subspaces in continuously varying Banach spaces. We derive basic …
Efficiently plans large MDPs with weak function approximations.
problem Planning in large MDPs with limited function approximation capabilities.
method Uses linear value function approximation with weak requirements and a generative oracle.
result Produces almost-optimal actions for any state with polynomial computation time.
Paper relaxes symmetry conditions for universal feature selection in noisy data.
problem Feature selection in noisy data with weak symmetry.
method Developed a universal feature selection framework using singular value decomposition of canonical dependence matrix.
result Selected features achieve asymptotically optimal error exponents up to a residual term.
FABLE incorporates instance features into PWS label models for improved performance.
problem Lack of instance features in existing label models limits their performance.
method FABLE uses a mixture of Bayesian label models and a Gaussian Process classifier to incorporate instance features.
result FABLE achieves the highest averaged performance across nine baselines on benchmark datasets.
Study on test risk dynamics in learning theory with stochastic gradient flow.
problem Understanding test risk in stochastic gradient flow dynamics.
method Path integral formulation for small learning rates, explicit computation for weak features.
result Explicit corrections due to stochastic term in dynamics, good agreement with simulations.
Improved machine learning models outperform their simpler counterparts by using imperfect labels.
problem Improving model performance using imperfect labels.
method Random feature ridge regression (RFRR) with a deterministic equivalent for excess test error.
result The student model can outperform the teacher model regardless of the teacher's scaling law, achieving the minimax optimal rate.
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.
In this paper we offer a method and algorithm, which make possible fully autonomous (unsupervised) detection of new classes, and learning following a very parsimonious training priming (few labeled data samples only). Moreover, new unknown classes may appear at a later stage and the proposed xClass method and algorithm…
Study shows how weak inverse anisotropic mean curvature flow behaves at infinity.
problem Understanding the asymptotic behavior of anisotropic mean curvature flow.
method Established local gradient estimates for anisotropic p-harmonic functions and weak solutions of IAMCF. result Weak IAMCF is asymptotic to the expanding Wulff shape solution at infinity.
The paper reveals three mechanisms for weak-to-strong generalization.
problem Understanding the mechanisms behind weak-to-strong generalization in imperfect labeling scenarios.
method Theoretical analysis of simple models including ridge regression and weighted ridge regression, and a nonlinear multi-index setting.
result A student model can compensate for a teacher's under-regularization and achieve lower test error.
Develops ELBD for efficient feature selection in VAE latent variables.
problem Feature selection in latent variables of VAE and its variants.
method ELBD score algorithm and weak convergence approximation for optimization.
result Effective feature selection and optimization of VAE models.
Study shows how information loss and operation loss are related in feature representations.
problem Understanding the relationship between information loss and operation loss in feature representations.
method Analyzes the interplay between weak information loss and operation loss in continuous representations.
result Specific forms of vanishing information loss imply vanishing MPE loss in classification.
W2S FT often outperforms weak teachers due to low intrinsic dimensionality.
problem Understanding why weak-to-strong finetuning outperforms weak models.
method Analyzing W2S in ridgeless regression setting, focusing on variance reduction.
result Weak teacher's variance is inherited by strong student in shared feature subspace, reduced in discrepancy subspace.
Concept drift in learning and classification occurs when the statistical properties of either the data features or target change over time; evidence of drift has appeared in search data, medical research, malware, web data, and video. Drift adaptation has not yet been addressed in high dimensional, noisy, low-context d…
Study improves cryptocurrency price prediction using unlabeled text data.
problem Predicting cryptocurrency returns from unlabelled text data.
method Introduced weak learning approach to finetune BERT on unlabeled text data.
result Finetuning pretrained NLP models with weak labels enhances forecast accuracy.
New method distinguishes feature relevance in non-linear contexts.
problem Finding relevant features with preserved redundancies.
method Random forest models and statistical methods.
result Distinguishes strong from weak feature relevance in non-linear problems.
AI techniques explain synthetic tabular data weaknesses.
problem Challenges in evaluating synthetic tabular data quality.
method Apply explainable AI to a binary detection classifier.
result Reveals inconsistencies, unrealistic dependencies, or missing patterns in synthetic data.
Deep networks have gained immense popularity in Computer Vision and other fields in the past few years due to their remarkable performance on recognition/classification tasks surpassing the state-of-the art. One of the keys to their success lies in the richness of the automatically learned features. In order to get ver…
SFP prunes ID features to improve OOD generalization without domain data.
problem Improving out-of-distribution (OOD) generalization in biased models.
method Spurious Feature-targeted model Pruning (SFP) framework.
result SFP achieves optimal OOD generalization by pruning ID features.
Deconfounding scores improve causal effect estimation with weak overlap.
problem Poor overlap in treatment and control groups makes causal effect estimators brittle.
method Introduces feature representations that improve overlap without introducing bias.
result Deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data.
We present a novel method - LIBRE - to learn an interpretable classifier, which materializes as a set of Boolean rules. LIBRE uses an ensemble of bottom-up weak learners operating on a random subset of features, which allows for the learning of rules that generalize well on unseen data even in imbalanced settings. Weak…
We connect high-dimensional subset selection and submodular maximization. Our results extend the work of Das and Kempe (2011) from the setting of linear regression to arbitrary objective functions. For greedy feature selection, this connection allows us to obtain strong multiplicative performance bounds on several meth…
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…
We propose a tree regularization framework, which enables many tree models to perform feature selection efficiently. The key idea of the regularization framework is to penalize selecting a new feature for splitting when its gain (e.g. information gain) is similar to the features used in previous splits. The regularizat…
Boosting weak learners to strong ones from aggregate labels is possible for LLP but not for MIL.
problem Boosting weak learners to strong ones from aggregate labels in learning from label proportions (LLP).
method Using a weak learner on large enough bags to obtain a strong learner for small bags in polynomial time.
result Boosting is possible for LLP but not for MIL.
This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test perform…
Although much progress has been made in classification with high-dimensional features \citep{Fan_Fan:2008, JGuo:2010, CaiSun:2014, PRXu:2014}, classification with ultrahigh-dimensional features, wherein the features much outnumber the sample size, defies most existing work. This paper introduces a novel and computation…
Labeling training data is one of the most costly bottlenecks in developing machine learning-based applications. We present a first-of-its-kind study showing how existing knowledge resources from across an organization can be used as weak supervision in order to bring development time and cost down by an order of magnit…
The "double descent" risk curve was proposed to qualitatively describe the out-of-sample prediction accuracy of variably-parameterized machine learning models. This article provides a precise mathematical analysis for the shape of this curve in two simple data models with the least squares/least norm predictor. Specifi…
Gradient descent amplifies random features in neural networks to useful ones.
problem Generalization in neural networks trained on corrupted data.
method Characterization of feature-learning process in two-layer ReLU networks trained by gradient descent.
result Gradient descent amplifies random features to useful ones, achieving near optimal generalization error.
Proposes a new method to find features affecting treatment effect distribution.
problem Existing methods fail to detect differences in treatment effect distribution parameters other than the mean.
method Formulates and estimates a feature importance measure that quantifies feature influence on potential outcome distribution discrepancies. Develops a feature selection algorithm to control type I error rate.
result Successfully discovers important features and outperforms existing mean-based methods.
This paper categorizes and analyzes existing outlying aspect mining methods.
problem Finding unique features in data objects that differ from others.
method Grouping and analyzing existing outlying aspect mining approaches in three categories.
result Comparison of strengths, weaknesses, and time complexities of different techniques.
This paper tackles the 'Clever Hans' effect in anomaly detection models.
problem The 'Clever Hans' effect undermines the generalization capability of anomaly detection models.
method An explainable AI procedure to highlight relevant features used by anomaly detection models.
result The Clever Hans effect is widespread in anomaly detection and occurs in many forms.
A new feature selection method using random forest and Kolmogorov filter.
problem Ultra-high dimensional data feature selection.
method Fused Kolmogorov filter with random forest based recursive feature elimination.
result Selection and L2 consistency under weak conditions. Study finds Bitcoin market efficient, no exploitable inefficiencies with neural networks.
problem Investigating market inefficiencies in Bitcoin using neural networks.
method Used a feedforward neural network with various asset-related input features.
result Adding more features does not improve prediction accuracy, and one feature set outperforms a buy-and-hold strategy.
Deep learning enhances smart fish farming through automated feature extraction.
problem Challenges in obtaining labeled data limit DL applications in aquaculture.
method Application of DL techniques in aquaculture, including live fish identification, species classification, and feeding decision-making.
result Deep learning's ability to automatically extract features is a significant contribution.
Proposes a new feature preprocessing method using kernel density integral transformation.
problem Feature preprocessing for tabular data in machine learning and statistics.
method Kernel density integral transformation as a drop-in replacement or improved alternative to min-max scaling and quantile transformation.
result Frequently outperforms min-max scaling and quantile transformation with hyperparameter tuning.
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.
This paper proposes a model-free and data-adaptive feature screening method for ultra-high dimensional datasets. The proposed method is based on the projection correlation which measures the dependence between two random vectors. This projection correlation based method does not require specifying a regression model an…
Unified method for local GBDT feature contributions.
problem Need for local model interpretation for GBDT.
method Unified computation mechanism for instance-level feature contributions.
result Unified computation mechanism for GBDT feature contributions.
Motivation: Biomarker discovery from high-dimensional data is a crucial problem with enormous applications in biology and medicine. It is also extremely challenging from a statistical viewpoint, but surprisingly few studies have investigated the relative strengths and weaknesses of the plethora of existing feature sele…