ACV improves structured data CV, handling dependence and noisy initial fits.
problem Structured data CV is slow due to expensive algorithm re-runs.
method Extend ACV to handle dependence and noisy initial fits.
result ACV provides accurate and efficient CV for structured data.
Neural networks learn clean data patterns first, then noisy data, leading to improved performance initially but deteriorating later.
problem Improvement in prediction error on clean data during early training of neural networks with noisy labels.
method Theoretical analysis and experiments to explore the dynamics of gradient descent and the impact of clean and noisy data.
result Neural networks prioritize learning clean data patterns first, leading to improved performance initially but deteriorating later due to diminishing gradient dominance of clean samples over noisy ones.
New method finds optimal training stop point with noisy labeled data.
problem Finding optimal training stop point with noisy labeled data.
method Analyzed training accuracy rate changes for different noise ratios to identify a training stop region. Developed a heuristic algorithm based on a small-learning assumption.
result Identified optimal training stop point at or close to maximum obtainable test accuracy.
Modern neural networks are typically trained in an over-parameterized regime where the parameters of the model far exceed the size of the training data. Such neural networks in principle have the capacity to (over)fit any set of labels including pure noise. Despite this, somewhat paradoxically, neural network models tr…
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.
CTEF fits ellipsoids to noisy data in any dimension.
problem Fitting ellipsoids to noisy data in arbitrary dimensions.
method Uses the Cayley transform to fit ellipsoids.
result CTEF outperforms other methods, especially when data are not uniformly distributed.
Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive poste…
Convolutional Neural Networks (CNNs) have emerged as highly successful tools for image generation, recovery, and restoration. A major contributing factor to this success is that convolutional networks impose strong prior assumptions about natural images. A surprising experiment that highlights this architectural bias t…
New ABC method improves Bézier simplex fitting for noisy data.
problem Overfitting in Bézier simplex fitting when sample points are not on the Pareto set.
method Extended Bézier simplex model to a probabilistic one and proposed a new learning algorithm based on approximate Bayesian computation (ABC) with Wasserstein distance.
result The new algorithm converges on a finite sample and outperforms deterministic methods on noisy instances.
Tensor-EM method learns MoLDS from complex, noisy data.
problem Modeling diverse temporal dynamics in neural data.
method Tensor-based moment method followed by EM updates.
result Tensor-EM achieves more reliable recovery and robustness.
Revisits CP tensor decomposition for noisy, non-orthogonal data.
problem Statistical optimality and convergence of ALS in noisy, non-orthogonal, higher-rank settings.
method Statistical analysis and TASD method for initialization.
result ALS with TASD achieves optimal error in rank-one setting within one or two iterations.
Deep networks can interpolate noisy data without losing generalization.
problem Characterizing the relationship between interpolation and generalization in overparameterized deep networks.
method Analyzing the loss landscape of neural network functions over volumes around training data points, varying model parameters and training epochs.
result Loss sharpness in the input space follows a double descent, with large models predicting noisy targets over larger volumes around training data points.
The method constructs arbitrage-free option surfaces from noisy quotes using Chebyshev bases and a fog post-fit layer.
problem Constructing arbitrage-free option price surfaces from noisy bid-ask quotes.
method Chebyshev tensor bases, linear sampling, no-arbitrage operators, quadratic objective, OSQP solvers, fog post-fit layer, Hamiltonian energy.
result High inside-spread coverage (98-99%) and low no-arbitrage violations (below 1%) in stable periods, controlled leakage in stressed periods.
Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization when mislabeled training examples are present. On the other hand, simple regularization methods like early-stopping can often achieve highly no…
Label aggregation makes learning robust to noisy labels.
problem Learning from noisy labels.
method Label aggregation and risk consistency.
result Aggregated labels lead to stronger consistency guarantees.
Learning from unlabeled and noisy data is one of the grand challenges of machine learning. As such, it has seen a flurry of research with new ideas proposed continuously. In this work, we revisit a classical idea: Stein's Unbiased Risk Estimator (SURE). We show that, in the context of image recovery, SURE and its gener…
Small initialization improves tensor recovery from noisy data.
problem Recovering low-tubal-rank tensors from noisy measurements.
method Factorized gradient descent with small initialization.
result Achieves nearly minimax optimal recovery error.
We develop a general theory for the goodness-of-fit test to non-linear models. In particular, we assume that the observations are noisy samples of a submanifold defined by a \yao{sufficiently smooth non-linear map}. The observation noise is additive Gaussian. Our main result shows that the "residual" of the model fit, …
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.
Neural networks can overfit perfectly to noisy data and then grok near-optimal generalization.
problem Neural networks' ability to overfit perfectly to noisy data and then generalize near-optimally.
method Two-layer ReLU networks trained by gradient descent on XOR cluster data.
result Neural networks can achieve perfect fit to noisy training data and then grok near-optimal generalization.
AMP method reconstructs rank-one matrices from noisy data efficiently.
problem Reconstructing rank-one matrices with prior structural information from noisy observations.
method Approximate Message Passing (AMP) with random initialization.
result AMP from random initialization converges rapidly and globally.
Paper presents efficient algorithms for reconstructing noisy pooled data.
problem Reconstructing hidden states from noisy pooled data.
method Simple and efficient distributed algorithms for two noise models.
result Our algorithms reconstruct exact initial states with high probability.
A new method approximates expected empirical loss for stochastic deep learning tasks.
problem Determining optimal step sizes for stochastic gradient descent in deep learning.
method Applying one-dimensional function fitting to noisy losses of vertical cross sections to approximate expected empirical loss.
result The method leads to a robust and straightforward optimization method that performs well across datasets and architectures.
We propose a unified framework for estimating low-rank matrices through nonconvex optimization based on gradient descent algorithm. Our framework is quite general and can be applied to both noisy and noiseless observations. In the general case with noisy observations, we show that our algorithm is guaranteed to linearl…
The first step to realize automatic experimental data analysis for fusion plasma experiments is fitting noisy data of temperature and density spatial profiles, which are obtained routinely. However, it has been difficult to construct algorithms that fit all the data without over- and under-fitting. In this paper, we sh…
Study on reproducibility in optimization with bounds on limits.
problem Limits of reproducibility in noisy or error-prone optimization procedures.
method Defined a quantitative measure of reproducibility and analyzed convex optimization settings.
result Revealed a fundamental trade-off between computation and reproducibility.
Paper tackles noisy labels by compressing feature representations.
problem Learning with noisy labels leads to overfitting and poor generalization.
method Introduces compression inductive bias using Dropout and Nested Dropout.
result Compression helps in combating label noise and improving performance.
The paper explores how linear neural networks can overfit without bias when data is well-behaved.
problem Understanding why linear neural networks can generalize well despite fitting noisy data.
method Analyzing two-layer linear neural networks trained with gradient flow, deriving bounds on excess risk.
result The excess risk depends on initialization quality and data covariance matrix properties.
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.
The study initiates a theoretical analysis of dynamic benchmarking models.
problem Lack of theoretical foundation and empirical studies in dynamic benchmarks.
method Examined two realizations of dynamic benchmarking: sequential and hierarchical dependency models.
result Sequential dynamic benchmarks show initial performance improvement but can stall after three rounds due to label noise.
The Extreme Deconvolution method fits a probability density to a dataset where each observation has Gaussian noise added with a known sample-specific covariance, originally intended for use with astronomical datasets. The existing fitting method is batch EM, which would not normally be applied to large datasets such as…
GONs improve predictions of maximizers from noisy black-box functions.
problem Estimating maximizers of noisy black-box functions.
method Global Optimization Networks (GONs) composed of invertible and unimodal functions.
result GONs outperform convex fits, GPR, and DNNs in prediction accuracy.
Deep models can fit noisy labels, but robustness and reliability are still issues.
problem Training deep models with noisy labels leads to unreliable uncertainty quantification.
method Analysis of conditional distribution over noisy labels and evaluation of robust loss functions.
result Strictly proper and robust loss functions preserve accuracy but do not guarantee reliability.
Paper analyzes convergence rate of noisy Bayesian Optimization with Expected Improvement.
problem Theoretical convergence behaviors and rates of Expected Improvement (EI) in Bayesian optimization.
method Analyzes Expected Improvement (EI) under Gaussian process (GP) prior assumption, considering noisy observations.
result Established asymptotic error bound and rate for GP-EI with noisy observations.
MARVEL curbs memorization of noisy labels in deep nets.
problem Noisy labels degrade deep net performance.
method MARVEL tracks classification margins to identify and abandon noisy instances.
result MARVEL outperforms baselines on noisy datasets.
PIE-PINN estimates elastic properties from noisy, low-res displacement data.
problem Estimating heterogeneous elastic properties from low-resolution, noisy data.
method Probabilistic Physics-Informed Neural Network (PIE-PINN) framework combining B-spline and hierarchical scale model.
result Robust estimation of Young's modulus and Poisson's ratio from noisy, low-resolution displacement data.
In this work we approach the task of learning multilingual word representations in an offline manner by fitting a generative latent variable model to a multilingual dictionary. We model equivalent words in different languages as different views of the same word generated by a common latent variable representing their l…
This paper proposes the use of an optimization algorithm, namely PSO to decide the initial centroids in K-means, to eventually get better accuracy. The vectorized notation of the optimal centroids can be thought of as entities in an optimization space, where the accuracy of K-means over a random subset of the data coul…
Computational models in fields such as computational neuroscience are often evaluated via stochastic simulation or numerical approximation. Fitting these models implies a difficult optimization problem over complex, possibly noisy parameter landscapes. Bayesian optimization (BO) has been successfully applied to solving…
Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large learning rate achieves better generalization soon after the learning rate is anne…
Variational Bayesian neural nets combine the flexibility of deep learning with Bayesian uncertainty estimation. Unfortunately, there is a tradeoff between cheap but simple variational families (e.g.~fully factorized) or expensive and complicated inference procedures. We show that natural gradient ascent with adaptive w…
Study semi-supervised learning with noisy proxy covariates, deriving bounds and showing gains.
problem Learning from noisy proxy covariates with scarce labels.
method Two-stage estimator learning kernel eigenfeatures from all proxy covariates and fitting a ridge predictor on labeled data.
result Finite sample bounds show fast labeled sample rates and consistent gains over supervised and semi-supervised baselines.
In label-noise learning, \textit{noise transition matrix}, denoting the probabilities that clean labels flip into noisy labels, plays a central role in building \textit{statistically consistent classifiers}. Existing theories have shown that the transition matrix can be learned by exploiting \textit{anchor points} (i.e…
Framework prevents deep learning models from memorizing noisy labels.
problem Deep learning models memorize noisy labels during early learning phase.
method Develops a technique that exploits early learning phase via regularization.
result Framework achieves robustness to noisy annotations on benchmarks and real-world datasets.
Normalizing flows improve density estimation from noisy data.
problem Estimating underlying density from noisy samples.
method Use normalizing flows for density estimation with arbitrary noise distributions, using amortized variational inference.
result Normalizing flows can outperform Gaussian mixtures for density deconvolution.
Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end. Although equipped with corrections for noisy labels, many learning methods in this area still suffer overfitting due to undesired memorization. In this paper, to relieve this issue, we propose …
Optimal multistage method solves noisy minimax problems.
problem Minimizing/maximizing in noisy conditions with smooth and strongly convex-strongly concave settings.
method Multistage Stochastic Gradient Descent Ascent (M-GDA) and Optimistic Gradient Descent Ascent (M-OGDA).
result Achieves optimal linear decay rate with respect to initial error and condition number.
Paper tackles noisy labels in deep learning networks.
problem Learning with noisy labels in deep neural networks.
method Sparse regularization strategy to approximate one-hot constraint.
result Improves performance of commonly-used loss functions in noisy labels and class imbalance.