Attention models can overfit without harming test performance.
problem Understanding benign overfitting in single-head attention models.
method Analyzing conditions for benign overfitting in a single-head softmax attention model.
result A single-head attention model can overfit without harming test performance under certain conditions.
ResNet models overfit benignly on Cifar10 but not on ImageNet due to label noise.
problem Understanding why benign overfitting fails in real-world classification tasks with label noise.
method Theoretical analysis of benign overfitting under a mild overparameterization setup.
result Benign overfitting can fail in the presence of label noise, unlike in heavy overparameterization settings.
The paper examines how spike strengths and alignments affect overfitting in linear regression models.
problem The impact of spike strengths and alignments on overfitting in linear regression models.
method Characterization of generalization error through exact expressions and analysis of spike strengths, aspect ratio, and target alignment.
result Increasing spike strength can lead to catastrophic overfitting before benign overfitting, especially in well-specified aligned problems.
Two-layer CNNs can overfit without harm under certain conditions.
problem Understanding when and how overfitting occurs in neural networks.
method Theoretical analysis of a two-layer CNN trained by gradient descent.
result A sharp phase transition between benign and harmful overfitting based on signal-to-noise ratio.
Framework for understanding overfitting and underfitting using information theory.
problem Understanding and preventing overfitting and underfitting in machine learning.
method Information-theoretic framework measuring algorithm capacity and dataset information transfer.
result Upper-bounding algorithm capacity and establishing its relationship to machine learning quantities.
Physics analogies explain machine learning overfitting control.
problem Understanding and controlling overfitting in machine learning.
method Analogies from physics and biology applied to algorithmic stability and GAN models.
result Physics formulas provide insights into reducing overfitting in machine learning.
Tests for overfitting in machine learning models.
problem Overfitting in high complexity models.
method Hypothesis test using concentration bounds.
result Valid test for identifying overfitting.
Paper tackles temporal overfitting in wind power curve modeling.
problem Temporal overfitting in wind power curve modeling.
method Proposes a Gaussian process-based method to partition and model time-invariant and time-varying components.
result Significant improvement in predicting responses for different time periods.
Meta learning works well with overparameterized models, a phenomenon called 'benign overfitting'.
problem Understanding why overparameterized models perform well in few-shot learning.
method Analyzed the generalization performance of gradient-based meta learning with an overparameterized meta linear regression model.
result Demonstrated that overparameterized meta learning can still generalize well, a phenomenon called 'benign overfitting'.
Diffusion models don't overfit, contrary to expectations.
problem Understanding generalization in diffusion models.
method Fundamental impossibility results and analysis of score matching.
result Diffusion models exhibit classical U-shaped loss curve, not double descent.
The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is overfitted to a test set is challenging as independent test sets drawn from the same data distribution are usually unavailable, while other …
A new exploration method for bandit and reinforcement learning.
problem Uncertainty quantification in exploration.
method Residual Overfit Method of Exploration (ROME).
result ROME drives exploration towards actions with overfitting.
Study the cost of overfitting in noisy KRR models.
problem Cost of overfitting in noisy kernel ridge regression.
method An agnostic view of overfitting cost as a function of sample size for any target function, using Gaussian universality ansatz and task eigenstructure.
result Characterization of benign, tempered, and catastrophic overfitting.
Study on benign overfitting in leaky ReLUs with moderate input dimensions.
problem Understanding when overfitting is beneficial in neural networks.
method Two-layer leaky ReLU networks trained with hinge loss, considering signal-to-noise ratio.
result Characterization of conditions for benign overfitting based on signal-to-noise ratio.
New insights into why neural networks can overfit without interpolating data.
problem Understanding why neural networks can overfit without interpolating data in fixed dimensions.
method Analyzing the smoothness of estimators and their derivatives.
result Benign overfitting is possible with estimators that have large enough derivatives, not just in high dimensions but also in fixed dimensions.
Meta-learning overfits both model and base learner; meta-augmentation helps.
problem Meta-learning overfits model and base learner.
method Use an information-theoretic framework to describe and demonstrate meta-augmentation.
result Meta-augmentation produces large complementary benefits to meta-regularization.
New insights into when benign overfitting occurs in linear and classification tasks.
problem Understanding when benign overfitting happens in linear and classification models.
method Analysis of a generic data model and comparison of predictors (minimum-norm interpolating and max-margin).
result The minimum-norm interpolating predictor is biased towards an inconsistent solution, preventing benign overfitting in linear regression.
Linear models can overfit without harming OOD generalization under certain conditions.
problem Understanding how overparameterized linear models generalize to out-of-distribution data.
method Analyzing overparameterized linear models under covariate shift, providing guarantees for OOD generalization.
result Benign overfitting occurs in standard ridge regression under OOD conditions, with specific structural conditions on target covariance.
Two-layer ReLU networks can overfit without harm, study finds.
problem Understanding when and how two-layer ReLU networks can overfit without harming generalization.
method Established algorithm-dependent risk bounds for two-layer ReLU convolutional neural networks with label-flipping noise.
result Gradient descent-trained ReLU networks can achieve near-zero training loss and Bayes optimal test risk.
New study finds many neural networks are not benignly overfitting.
problem Understanding the behavior of overfitting in neural networks.
method Exploring kernel ridge regression and deep neural networks to identify overfitting behaviors.
result Many interpolating methods, including neural networks, exhibit tempered overfitting rather than benign or catastrophic.
Overfitting can make models vulnerable to adversarial attacks even if they are robust to standard risks.
problem Adversarial robustness of models trained to fit noisy data.
method Theoretical analysis of overparameterized linear models and neural networks.
result Overfitting can lead to adversarial vulnerability, even if the model is robust to standard risks.
TPBS models improve robustness to overfitting with localized Dirichlet energy regularization.
problem Global Dirichlet energy-based regularization fails for TPBS models due to perfect interpolation.
method Propose local Dirichlet energy regularization and two inference estimators.
result TPBS models outperform neural networks in overfitting regimes and maintain competitive performance otherwise.
New method targets sparsity to prevent overfitting in deep nets.
problem Overfitting in deep neural networks with small datasets.
method Targeted sparsity regularization to visualize and counteract overfitting.
result Significant increase in image classification performance without overfitting.
Bayesian model selection can be misled by ELBO under certain conditions.
problem Misleading model selection when using ELBO for Bayesian inference.
method Analysis of ELBO-based hyperparameter learning in a simple regression model.
result Bayesian model selection can prefer overfit models when ELBO is used, contrary to evidence.
New analysis shows bias term affects conditions for benign overfitting in linear classifiers.
problem Understanding conditions for good generalization in linear classifiers with bias terms.
method Extending Hashimoto et al.'s results to include bias terms, analyzing covariance structure and label noise.
result Benign overfitting persists in linear classifiers with bias terms, with new constraints on data's covariance structure.
The paper explores how overfitting can lead to better predictions in high-dimensional data.
problem Understanding the behavior of linear models in high-dimensional settings with more predictors than observations.
method Analysis of ordinary least squares, penalized least squares, and spectral shrinkage estimates.
result The phenomenon of double descent, where model performance can improve with increasing model complexity.
Paper explains adversarial training's robust overfitting through a minimax game perspective.
problem Adversarial training suffers from robust overfitting after learning rate decay.
method Viewing adversarial training as a dynamic minimax game, analyzing how LR decay breaks balance and leads to overfitting.
result ReBalanced Adversarial Training (ReBAT) alleviates robust overfitting without sacrificing robustness.
We investigate under and overfitting in Generative Adversarial Networks (GANs), using discriminators unseen by the generator to measure generalization. We find that the model capacity of the discriminator has a significant effect on the generator's model quality, and that the generator's poor performance coincides with…
Deep learning models can overfit noisy data without losing generalization.
problem Understanding the generalization of deep learning models in noisy data.
method Empirical investigation of epoch-wise double descent in fully connected neural networks trained on CIFAR-10 with 30% label noise.
result The model achieves strong re-generalization on test data after overfitting noisy training data, corresponding to a 'benign overfitting' state.
New insights into how overfitting affects neural networks' performance.
problem Understanding the generalization of overfitted two-layer neural networks.
method Analyzing the NTK model with ReLU activation, focusing on min ℓ2-norm solutions. result Generalization error of overfitted NTK models approaches a small limiting value, even with infinite neurons and samples.
Deep neural networks can generalize well even with perfect fits to noisy data.
problem Understanding the conditions under which deep neural networks generalize well in the presence of noise.
method Comprehensive study of linear maximum margin classifiers, focusing on noisy and noiseless cases.
result Discovery of a phase transition in test error bounds for the noisy model.
Adversarial training overfits, harming robustness; early stopping fixes this.
problem Adversarial robustness in deep learning overfits to training data.
method Empirical study of adversarially trained deep networks.
result Overfitting to training data harms robust performance in adversarial training.
Random Forests don't overfit, challenging the double-descent theory.
problem The overfitting behavior of Random Forests.
method Challenged the double-descent curve theory by analyzing the performance of Random Forests and proposing a new approach to diversity in ensembles.
result Random Forests do not exhibit a double-descent curve but rather a single descent, indicating they do not overfit in the classic sense.
In-sample overfitting is a drawback of any backtest-based investment strategy. It is thus of paramount importance to have an understanding of why and how the in-sample overfitting occurs. In this article we propose a simple framework that allows one to model and quantify in-sample PnL overfitting. This allows us to com…
The paper tackles backtest overfitting in cryptocurrency trading using deep reinforcement learning.
problem Backtest overfitting in deep reinforcement learning for cryptocurrency trading.
method Formulated hypothesis test for overfitting detection, trained agents, estimated overfitting probability, and rejected overfitted agents.
result Less overfitted deep reinforcement learning agents outperformed more overfitted agents and market benchmarks.
The paper tackles manifold overfitting in deep generative models.
problem Manifold overfitting occurs when generative models learn the manifold itself instead of the distribution on it.
method The authors propose a two-step procedure: dimensionality reduction followed by maximum-likelihood density estimation.
result The two-step procedure avoids manifold overfitting and enables density estimation on learned manifolds.
Study shows linear models can predict CATE without overfitting, even with large data.
problem Overfitting in large-scale causal inference models.
method Investigated linear models for CATE prediction, considering samples with switching distributions.
result IPW-learner converges risk to zero if propensity score is known, while T-learner fails to achieve consistency.
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process (MDP). We provide a general framework for analyzing this scenario, which we use to de…
This work characterizes benign overfitting in Vision Transformers.
problem Understanding generalization of Vision Transformers when trained to overfit.
method Gradient descent on a data distribution model, focusing on self-attention layer and softmax.
result Established a condition to distinguish between small and large test errors based on signal-to-noise ratio.
ARO overfits by making constraints dependent on uncertainty, leading to brittleness.
problem ARO's adaptive policies become brittle when realizations fall outside the uncertainty set.
method Assigning constraint-specific uncertainty set sizes with probabilistic guarantees.
result Regularization through specific uncertainty set sizes ensures stability and flexibility.
Neural networks can interpolate noisy data and still generalize well.
problem Generalization of neural networks trained on noisy data.
method Two-layer neural networks trained to interpolation by gradient descent on corrupted labels.
result Neural networks can achieve zero training error and optimal test error.
The paper explores how noise in features can lead to benign overfitting in machine learning models.
problem Understanding the conditions for benign overfitting in machine learning models.
method Examined random feature models, specifically two-layer neural networks with fixed first layer weights, and analyzed the role of noise in features.
result Noise in features plays an important implicit regularization role in the phenomenon of benign overfitting.
We prove overfitting in minimal and random NNs, tempering the effect.
problem Overfitting in minimal and random neural networks.
method Analyzing binary weight fitting to noisy data, proving overfitting is tempered.
result The overfitting of minimal and random neural networks is tempered.
This paper tackles overfitting in CTR models by introducing Multi-Epoch learning with Data Augmentation.
problem Overfitting of the embedding layer in CTR models during multi-epoch training.
method Introduces Multi-Epoch learning with Data Augmentation (MEDA) framework to reduce overfitting and enhance performance.
result MEDA minimizes overfitting and achieves data augmentation through varied embedding spaces, improving performance without overfitting.
Adaptive regularization prevents overfitting in large-scale sparse feature models.
problem Overfitting in models with large-scale sparse categorical features.
method Adaptive regularization of embedding layers' norm budget.
result Improves model performance within a single epoch and prevents multi-epoch performance degradation.
Double descent in portfolio optimization shows improved performance with complexity, then declines, due to overfitting.
problem Improving portfolio optimization performance with model complexity.
method Investigates the relationship between model complexity and out-of-sample performance in mean-variance portfolio optimization.
result Performance of low-dimensional models initially improves with complexity but declines due to overfitting. High-dimensional models show double ascent Sharpe ratio curve.
New approach quantifies overfitting in high-dimensional regression.
problem Quantifying and avoiding overfitting in large neural networks.
method Information bottleneck theory to minimize residual information while maximizing relevant bits.
result Characterized the relative information efficiency of randomized regression compared to optimal algorithms.
End-to-end meta-learned system for image compression.
problem Reducing the gap between training and inference conditions in image compression.
method Model-Agnostic Meta-learning approach for latent tensor overfitting and updating encoder and decoder networks.
result Meta-learned system achieves better compression performance compared to traditional methods.