Bayesian relabeling improves PU learning for biased positive examples.
problem Learning from biased positive examples in PU learning.
method Probabilistic-gap based PU learning with Bayesian optimal relabeling and kernel mean matching.
result The proposed algorithm improves performance on real-world datasets.
New method improves meta-reinforcement learning efficiency.
problem Sample inefficiency in meta-reinforcement learning.
method Hindsight Foresight Relabeling (HFR) method.
result HFR improves performance on various meta-reinforcement learning tasks.
Rewriting history improves RL algorithms for solving multiple tasks.
problem Improving sample efficiency in multi-task reinforcement learning.
method Introducing hindsight relabeling as inverse RL to generalize goal-relabeling techniques.
result Relabeling data using inverse RL accelerates learning in multi-task settings.
Identifies minimal training subset to flip a prediction.
problem Flipping predictions in machine learning models.
method Extended influence function for relabeling minimal subset.
result Relabeling fewer than 2% of training points can flip a prediction.
Cincer cleans both new and past data by identifying and relabeling suspicious and counter-examples.
problem Sequential learning under label noise, especially in applications with human supervision.
method Cincer uses example-based explanations to identify and relabel suspicious and counter-examples, leveraging Fisher information matrix approximation.
result Cincer achieves better data and models by clarifying the model's suspicions, especially with FIM approximation.
Generalized Hindsight improves RL by reusing data from one task for another.
problem High sample complexity in reinforcement learning due to wasted uninformative data.
method Approximate inverse reinforcement learning to relabel behaviors with better-suited tasks.
result Efficient reuse of samples, reducing sample complexity on multi-task RL tasks.
Paper proposes methods to improve SVM classifiers in noisy data scenarios.
problem Improving SVM classifiers when training data contains label noise.
method Mixed Integer Linear and Non Linear models with relabeling and clustering.
result Effective methods improve SVM performance in noisy data scenarios.
Method detects and relabels noisy image labels to improve DNN performance.
problem Label noise in training images harms DNN generalization.
method Identifies noisy labels based on predictive uncertainty changes over training.
result Iterative relabeling of noisy labels improves DNN performance.
Cold posteriors improve Bayesian neural networks by reducing overestimation of aleatoric uncertainty.
problem Overestimation of aleatoric uncertainty in Bayesian neural networks.
method Tuning the temperature of the posterior on a validation set.
result Reducing temperature leads to better reflection of true prior beliefs.
Improved anomaly detection for launch vehicle propulsion systems using LSTM and statistical relabeling.
problem Detecting anomalies in real-time telemetry data for launch vehicles.
method Utilized LSTM networks for anomaly classification, introduced a statistical detector based on Mahalanobis distance and forward-backward detection fractions to adjust training labels.
result Precision and recall of the LSTM classifier improved by 7% and 22% respectively after statistical relabeling.
Algorithm learns new tasks efficiently from past experience.
problem Lack of robustness to distributional shift in meta-reinforcement learning.
method Model Identification and Experience Relabeling (MIER) using dynamics models.
result Efficient extrapolation to out-of-distribution tasks.
Study matches two noisy point clouds with geometric transformations and relabeling.
problem Matching two noisy point clouds with orthogonal transformations and relabeling.
method Information-theoretic results and Ping-Pong algorithm for computational alignment.
result The Ping-Pong algorithm retrieves the planted signal after one step.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.
When Daan Krammer and Stephen Bigelow independently proved that braid groups are linear, they used the Lawrence-Krammer-Bigelow representation for generic values of its variables q and t. The t variable is closely connected to the traditional Garside structure of the braid group and plays a major role in Krammer's alge…
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.
FairUDT uses uplift decision trees to detect and mitigate discrimination in training data.
problem Bias in machine learning classifiers due to historical discrimination or underrepresentation of minority groups.
method Integrates uplift modeling with decision trees and introduces a modified leaf relabeling approach for fairness.
result Achieves an acceptable accuracy-discrimination tradeoff while maintaining interpretability.
HIGhER uses language to generate new instructions for better learning from mistakes.
problem Improving instruction following in reinforcement learning environments.
method Hindsight Generation for Experience Replay (HIGhER) that learns from mistakes and relabels episodes.
result HIGhER enhances instruction following in reinforcement learning environments.
Method solves long-horizon robotic tasks via imitation and reinforcement learning.
problem Long-horizon robotic tasks with complex sequences of actions.
method Two-phase approach: imitation learning followed by reinforcement learning.
result Method can scale to challenging long-horizon tasks.
The study examines how permutation-based optimization performance varies across different function representations.
problem Understanding how the order of function evaluations affects optimization performance.
method Iterative search setting with sampling without replacement, algebraic function recombination, correlation analysis, hierarchical clustering, PCA, ANOVA.
result Algebraically modified benchmarks yield stable re-rankings and coherent clusters of functions and sampling policies, indicating non-additive search effort.
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an ind…
GWINs improve classifier accuracy by translating uncertain observations.
problem Improving accuracy of uncertain observations in classifiers.
method Generative network recovers correct observation distributions, reject option allows for uncertain predictions.
result GWINs significantly improve classifier accuracy on benchmark datasets.
Study efficient interactive learning for structured outputs with reliable computation.
problem Interactive learning with noisy labels and structured output spaces.
method Identify and utilize CRISPs (probabilistic models) that guarantee reliable and efficient computation of probabilistic quantities.
result CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
We propose new positive definite kernels for permutations. First we introduce a weighted version of the Kendall kernel, which allows to weight unequally the contributions of different item pairs in the permutations depending on their ranks. Like the Kendall kernel, we show that the weighted version is invariant to rela…
Improves k-NN for monotonic data with robustness against noise.
problem Class noise in real-life data violates monotonic constraints in k-NN.
method Monotonic Fuzzy k-NN (MonFkNN) with new fuzzy membership calculation.
result Significant accuracy improvements and robustness against monotonic noise.
The paper proposes a method to adapt models from source to target domains by calibrating their predictive uncertainties.
problem Inferring class labels for unlabeled target domain given a related labeled source dataset.
method The approach involves calibrating predictive uncertainties quantified as Renyi entropy, using variational Bayes learning and sample variance regularization.
result The proposed method effectively adapts models across three domain-adaptation tasks.
We survey the role of symmetry in diffeomorphic registration of landmarks, curves, surfaces, images and higher-order data. The infinite dimensional problem of finding correspondences between objects can for a range of concrete data types be reduced resulting in compact representations of shape and spatial structure. Th…
Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We prese…
Proposes autoencoding with random forests using spectral graph theory.
problem Learning low-dimensional embeddings of random forest models.
method Combines nonparametric statistics and spectral graph theory for optimization.
result Establishes a universal consistent decoder for random forest models.
A new permutation method improves two-sample testing power.
problem Two-sample testing with improved power and validity.
method Structured block-restricted cross-swaps.
result Block-restricted permutations achieve higher power than full permutations.
Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.
problem Understanding and quantifying data poisoning in linear models.
method Analysis of ridge least squares with an unpenalized intercept, using resolvent techniques and random matrix theory.
result Closed-form limits for the poisoned score, revealing scaling laws and weight alignment with the poisoning direction.
Novel discretization of Euler equations for incompressible fluids.
problem Nonholonomic constraints in discrete fluid dynamics.
method Vakonomic perspective on Lie group of volume-preserving diffeomorphisms.
result Discrete fluid trajectories remain geodesics on a sub-Riemannian manifold.
Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The problem of detecting such novel classes has been addressed in the literature, but mos…
Study investigates one-shot semi-supervised learning for image classification.
problem Training deep networks requires many labeled samples, limiting adoption.
method Empirical investigation of FixMatch method for one-shot semi-supervised learning.
result Uneven class accuracy is a barrier to high performance in one-shot semi-supervised learning.
CNNs improve transient detection in DES-SN images.
problem Automated identification of transients in astronomical images.
method Convolutional Neural Networks (CNNs) for image classification.
result CNNs achieve efficiency in identifying non-artifacts from artifacts.
A new measure of causal influence quantifies intrinsic contributions in DAGs.
problem Quantifying intrinsic causal contributions in Directed Acyclic Graphs (DAGs).
method Recursive decomposition of node contributions, structure-preserving interventions, Shapley symmetrization.
result A measure of intrinsic causal contribution that is invariant to node relabeling.
ACTRCE uses natural language to improve reinforcement learning performance.
problem Sparse reward in reinforcement learning.
method Extends HER framework with natural language goal representation.
result ACTRCE can solve challenging 3D navigation tasks and generalize to unseen instructions.
New MCMC method tackles label-switching problem for clustering.
problem Label-switching problem impedes MCMC efficiency in discrete clustering.
method Formulated optimal transport couplings for partition space.
result Our method efficiently overcomes label-switching problem.
This paper aims to incorporate passive symmetries in machine learning for better generalization.
problem Machine learning's reliance on arbitrary choices leads to passive symmetries that can limit generalization.
method Translation among physics, mathematics, and machine learning to understand and implement passive symmetries.
result Respecting passive symmetries can improve machine learning's ability to generalize.
The paper proposes a method for a robot to learn skills from imagined goals.
problem Training robots to perform a wide range of tasks with raw sensory input.
method Combining unsupervised representation learning and reinforcement learning of goal-conditioned policies.
result The method learns skills that can operate on raw image observations and outperforms prior techniques.
Clustering ensemble is one of the most recent advances in unsupervised learning. It aims to combine the clustering results obtained using different algorithms or from different runs of the same clustering algorithm for the same data set, this is accomplished using on a consensus function, the efficiency and accuracy of…
Study shows label errors impact model disparity metrics, proposing mitigation methods.
problem Impact of label errors on model disparity metrics.
method Empirical study, characterizing label error effects; proposing estimation and relabeling methods.
result Label errors significantly affect model disparity metrics, particularly for minority groups.
Paper proposes a method to learn goal-reaching behaviors from scratch using imitation learning.
problem Current reinforcement learning algorithms are brittle and require expert demonstrations.
method Iterated supervised learning where agents relabel and imitate generated trajectories.
result Improved goal-reaching performance and robustness over current RL algorithms.
MBML improves multi-task RL by inferring task identity from state-action pairs.
problem Multi-task batch reinforcement learning with unseen tasks.
method MBML uses triplet loss and relabeling to robustify task inference.
result Significantly faster convergence on unseen tasks compared to random initialization.
New uniformity tester ensures consistent results across different samples.
problem Non-replicable behavior of uniformity testing algorithms.
method Develops a replicable uniformity tester with improved sample complexity.
result Achieves nearly linear dependence on replicability factor ρ. We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time spot follows a Gaussian mixture distribution, a fact exploited to softly matc…
SymmPI predicts unobserved values under group symmetries, improving over existing methods.
problem Quantifying uncertainty in predictions under group symmetries.
method Distributional equivariant transformations to preserve symmetries.
result SymmPI provides valid coverage and performs favorably in simulations and empirical data.
Proposes DeGLIF to denoise graph data for label noise robustness.
problem Label noise in graph data makes node classification challenging.
method Uses leave-one-out influence function to denoise graph data.
result DeGLIF improves accuracy in node classification on noisy datasets.
This work relaxes GNN symmetries to approximate automorphisms, improving model performance.
problem Improving graph neural network performance on asymmetric graphs.
method Formalizing approximate symmetries via graph coarsening, introducing a bias-variance formula.
result Best generalization performance achieved by choosing a larger symmetry group than automorphisms but smaller than permutations.