FANNet analyzes noise tolerance and training bias in neural networks.
problem Low noise tolerance and input sensitivity in neural networks lead to failures on unseen inputs.
method Formal analysis using model checking under different noise ranges.
result Noise tolerance of ±11% for the trained network, sensitive input nodes identified, and biasness confirmed. Framework for private, noise-tolerant, and efficient learning algorithms.
problem Private and efficient learning of large-margin halfspaces in noisy environments.
method Simple framework using differential privacy and noise tolerance conditions.
result Noise-tolerant and private PAC learners for large-margin halfspaces with sample complexity independent of dimension.
Paper shows how to build fair classifiers with noisy sensitive features.
problem Fairness in learning with noisy sensitive features.
method Developed a method to adjust tolerance for fairness when sensitive features are noisy.
result It is possible to build fair classifiers with noisy sensitive features.
Paper designs a time delay reservoir using stochastic logic.
problem Designing a robust time delay reservoir for noise-tolerant classification problems.
method Stochastic logic approach with re-seeding method.
result The proposed design performs well on noise-tolerant classification problems.
GRAPE improves RL policy evaluation in noisy environments.
problem Noise in real-world RL environments makes policy evaluation algorithms inefficient or prone to errors.
method GRAPE combines gap-increasing value update operators and off-policy eligibility trace.
result GRAPE is more efficient and noise-tolerant than existing methods.
Improved graph classification with noisy labels using GNNs and loss correction.
problem Robustness of GNNs to symmetric label noise.
method Combining GNNs with loss correction methods.
result Test accuracy improvement under noisy conditions.
Study efficient learning of halfspaces with constant noise tolerance.
problem Learning halfspaces in the presence of both instance and label corruption.
method Develops an algorithm to minimize reweighted hinge loss for robustness.
result Achieves constant noise tolerance for halfspace learning.
New loss functions make deep nets robust to noisy labels.
problem Label noise in training data affects deep neural networks.
method Developed conditions for loss functions to be robust to label noise.
result Mean absolute value loss is inherently robust to label noise.
A new deep metric learning method pulls embeddings towards dense clusters to improve classification accuracy.
problem Improving classification accuracy in deep metric learning models.
method Density Aware Metric Learning (DAML) which pulls embeddings towards the densest regions of clusters for each class.
result DAML achieves faster convergence and higher generalizability compared to existing methods.
New methods for handling time-varying label noise in time series classification.
problem Temporal label noise in time series classification tasks.
method Proposed methods to estimate temporal label noise function directly from data.
result Our methods lead to state-of-the-art performance under diverse types of temporal label noise.
QRPNNs use quaternion-valued recurrent correlation neural networks to solve cross-talk issues.
problem Cross-talk problem in QRCNNs.
method Combining non-local projection learning with QRCNNs.
result QRPNNs exhibit greater storage capacity and noise tolerance.
Noise-tolerant algorithm for online matrix completion with provable guarantees.
problem Recovering an incomplete matrix with online noisy columns.
method Adaptive sampling algorithms for bounded and sparse random noise models.
result Strong guarantees for matrix recovery with near-optimal sample complexity.
New algorithms learn from comparisons to classify data robustly to noise.
problem Learning robust classifiers from noisy data efficiently.
method Introducing comparison queries to active learning, providing noise-tolerant classifiers.
result First time and query efficient algorithms for robust learning under bounded noise.
New method creates imperceptible and robust adversarial examples.
problem Vulnerability of neural networks to adversarial examples.
method Human perceptual system consideration and maximizing noise tolerance.
result Efficacy demonstrated through experimental results.
Paper tackles interactive learning with noisy labels and comparisons, showing how comparison oracles can improve learning efficiency.
problem Interactive learning with noisy labels and comparisons.
method Characterizes comparison oracle as threshold function learning problem, presents algorithm with query complexity analysis.
result Lower bounds show almost optimal label and total query complexity.
We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random e…
Improved sample complexity for learning halfspaces with malicious noise.
problem Efficiently learning halfspaces in the presence of malicious noise.
method New analysis of Awasthi et al. algorithm with matrix Chernoff inequality and localization schemes.
result Achieved near-optimal sample complexity of ildeO(d) for isotropic log-concave distributions. Interactive learning framework for various settings.
problem Various interactive learning settings.
method Adapted active learning algorithm for interactive structure discovery.
result Noise-tolerant algorithm with favorable query complexity.
Paper proves noise-tolerant SSC using greedy methods under coherence conditions.
problem Proving noise-tolerant SSC using greedy methods under coherence conditions.
method Derives coherence-based sufficient conditions for correct neighbor identification using MP/OMP in the presence of bounded noise.
result MP/OMP succeed in identifying correct neighbors under certain noise levels, leading to higher clustering accuracy.
New particle-based method improves semi-supervised learning robustness to label noise.
problem Label noise degrades semi-supervised learning accuracy.
method Particle competition and cooperation algorithm for robust semi-supervised learning.
result Improved robustness to label noise compared to existing methods.
Algorithm learns binary function efficiently under arbitrary covariate shift.
problem Learning binary function under arbitrary distributions P and Q.
method PQ-learning algorithm using reliable learner with selective classification.
result Polynomial-time algorithm for covariate shift learning.
We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and compu…
Efficiently learns halfspaces with malicious noise, near-optimal label complexity.
problem Learning s-sparse halfspaces under malicious label noise. method Active learning algorithm with instance reweighting and empirical risk minimization.
result Near-optimal label complexity of O(slog4d/ε) and noise tolerance Ω(ε). A method to train deep neural networks on noisy labeled data.
problem Training deep neural networks on noisy labeled data causes performance degradation.
method A noise-tolerant training algorithm that simulates actual training with synthetic noisy labels.
result The proposed method outperforms state-of-the-art baselines on noisy CIFAR-10 and Clothing1M datasets.
TensorHyper-VQC improves VQC scalability and robustness.
problem Scalability and noise sensitivity in VQC.
method Tensor-train-guided hypernetwork framework.
result TensorHyper-VQC achieves superior performance and robust noise tolerance.
Cross-regularization adapts model complexity during training.
problem Manual tuning of model complexity for overfitting prevention.
method Directly adapts regularization parameters through validation gradients during training.
result Organic emergence of architecture-specific regularization during training.
A new Metropolis-Hastings method reduces the cost of testing for large datasets.
problem Reducing the cost of Metropolis-Hastings tests for large datasets.
method Uses small minibatches and a novel Barker acceptance test with additive correction.
result Achieves arbitrarily small batch sizes by adjusting proposal step size or temperature.
New insights on robust learning under strong noise models.
problem Challenging label-noise models in robust learning.
method Extending statistical query framework to more general noise models and using evolutionary algorithms.
result First polynomial time algorithm for learning linear threshold functions with arbitrarily small excess error in presence of Tsybakov noise.
New tensor decomposition method handles more noise and higher orders.
problem Efficient tensor decomposition for noisy data.
method Two-mode higher-order SVD (HOSVD) with Kruskal's theorem.
result Proves higher noise tolerance and high accuracy.
Recently, a family of tractable NMF algorithms have been proposed under the assumption that the data matrix satisfies a separability condition Donoho & Stodden (2003); Arora et al. (2012). Geometrically, this condition reformulates the NMF problem as that of finding the extreme rays of the conical hull of a finite set …
This paper investigates the problem of determining a binary-valued function through a sequence of strategically selected queries. The focus is an algorithm called Generalized Binary Search (GBS). GBS is a well-known greedy algorithm for determining a binary-valued function through a sequence of strategically selected q…
Unified approach to learning from noisy labels using auxiliary clean labels.
problem Learning from noisy labels in real-world applications.
method Rotational-Decoupling Consistency Regularization (RDCR) framework integrating consistency-based methods and self-supervised rotation task.
result RDCR achieves comparable or superior performance than state-of-the-art methods under small noise, significantly outperforming existing methods under large noise.
A method for estimating parameters from entangled single-sample distributions, robust to high-noise data.
problem Estimating common parameters from entangled single-sample distributions.
method Iterative trimming of samples to estimate the parameter.
result The method can tolerate a constant fraction of high-noise data points.
We consider a class of constrained optimization problems with a possibly nonconvex non-Lipschitz objective and a convex feasible set being the intersection of a polyhedron and a possibly degenerate ellipsoid. Such problems have a wide range of applications in data science, where the objective is used for inducing spars…
We consider the noisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under resource (communication, memory or privacy) constraints. Existing analysis of the noisy power method shows an unsatisfactory dependency over …
Novel loss functions improve decision tree learning from noisy data.
problem Training decision trees with noisy labels.
method Introducing distribution losses and a new negative exponential loss.
result The negative exponential loss leads to efficient and robust decision tree learning.
The paper analyzes how GANs converge using dual metric flows.
problem Understanding the convergence dynamics of GANs.
method Investigates the convergence of GANs using dual metric flows, formal definitions, and proving convergence.
result GAN learning dynamics converge to a limit when learning rate is small.
Algorithm learns neural networks with two layers in polynomial time.
problem Learning neural networks with two nonlinear layers without assumptions.
method Isotonic regression combined with kernel methods.
result First provably efficient algorithm for two-layer neural networks.
We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear separators. We consider both the malicious noise model and the adversarial label nois…
Unified framework for realizable and agnostic learning.
problem Lack of a unified theory for realizable and agnostic learnability.
method Three-line blackbox reduction.
result Unified understanding across various learning settings.
Paper improves robust subspace clustering for noisy and missing data.
problem Clustering points on multiple subspaces with noise and missing data.
method Robust variant of sparse subspace clustering (SSC) with explicit noise and missing data tolerance bounds.
result Establishes clustering guarantees for higher tolerance to noise and missing data.
Paper proposes SL to improve DNN learning with noisy labels.
problem Learning with noisy labels in deep neural networks.
method Symmetric Cross Entropy (SL) with Reverse Cross Entropy (RCE).
result SL outperforms state-of-the-art methods on various datasets.
Generates low-dimensional node vectors for graphs with privacy while preserving structural preferences.
problem Publishing graph node vectors can leak sensitive individual information.
method SE-PrivGEmb, a skip-gram based technique with a unified noise tolerance mechanism and negative sampling probabilities.
result Our method outperforms existing methods in structural equivalence and link prediction tasks.
New algorithms for learning under s-concave distributions, including Pareto and t-distributions.
problem Learning under broad and natural generalizations of log-concave distributions, including fat-tailed ones.
method Introduce new convex geometry tools to study s-concave distributions and use these properties to provide bounds on learning quantities. result Significantly generalize prior results for margin-based, disagreement-based, and passive learning of intersections of halfspaces.
New algorithm recovers high-dimensional linear regression vectors without sparsity assumptions.
problem Efficiently recovering unknown vector β* from noisy linear observations in high dimensions.
method Proposes a polynomial-time algorithm based on LLL lattice basis reduction assuming rational entries with the same denominator.
result Algorithm successfully recovers β* for a large class of distributions and non-zero noise, even with small noise and one observation.
New findings on boosting sample complexity and implications for hardcore theorem.
problem Understanding the sample complexity of smooth boosting and its implications.
method Analyzing the sample complexity of smooth boosting and relating it to the hardcore theorem.
result The sample complexity of smooth boosting matches existing overhead and provides a separation from distribution-independent boosting.
PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.
problem Optimizing unknown functions with noisy, delayed, and multi-fidelity feedbacks.
method ProCrastinated Tree Search (PCTS) with DUCB1 and DUCBV algorithms.
result PCTS achieves better regret bounds for delayed, noisy, and multi-fidelity feedbacks.
Paper tackles noisy neural networks and proposes a method to enhance their robustness.
problem Noisy neural networks struggle with random continuous noise in weights.
method Knowledge distillation combined with noise injection during training.
result Models achieve up to twice greater noise tolerance.