Theoretical analysis shows PU and NU learning can outperform PN learning under certain conditions.
problem Comparing PU and PN learning without negative data.
method Theoretical analysis based on upper bounds on estimation errors.
result Conditions under which PU and NU learning outperform PN learning are identified and proven.
Paper presents a neural network for managing interference in DSA.
problem Managing interference between primary and secondary networks in DSA.
method Artificial neural network predicts CR's effect on PN without direct communication.
result Fine-tuned transmit power control and higher transmission opportunities for CRs.
We study quasi-morphisms on the groups Pn of pure braids on n strings and on the group D of compactly supported area-preserving diffeomorphisms of an open two-dimensional disc. We show that it is possible to build quasi-morphisms on Pn by using knot invariants which satisfy some special properties. In particular, we st…
PNs model distributional uncertainty in predictive AI predictions.
problem Uncertainty in AI predictions, distinguishing between model and data uncertainty.
method Prior Networks (PNs) parameterize a prior distribution over predictive distributions.
result PNs outperform previous methods in identifying out-of-distribution samples and detecting misclassification.
Study geometric relations between submanifolds of arbitrary codimension.
problem Understanding the geometric configuration of submanifolds of arbitrary codimension.
method Obtained relations between the geometry of submanifolds and their boundaries.
result Ellipticity of generalized Newton transformations implies tranversality and total geodesy.
A quantum system can be entirely described by the Kähler structure of the projective space P(H) associated to the Hilbert space H of possible states; this is the so-called geometrical formulation of quantum mechanics. In this paper, we give an explicit link between the geometrical formulation (of finite dimensional qua…
We use bordered Floer homology to give a formula for the knot Floer homology of any (p, pn+1)-cable of a thin knot K in terms of Delta_K(t), tau(K), p, and n. We also give a formula for the Ozsvath-Szabo concordance invariant tau(K_{p, pn+1}) in terms of tau(K), p, and n, and a formula for tau(K_{p,q}) for almost all r…
Algorithm finds minimal standardizer of parabolic subgroups in Artin-Tits groups.
problem Computing minimal standardizer of parabolic subgroups in Artin-Tits groups.
method Geometrical and algebraic algorithms to compute p n pn p n -normal form of a central element. result Minimal standardizer computation simplified to p n pn p n -normal form. Let p and n be positive integers with p>1, and let E(p,n) be the oriented 3-manifold obtained by performing pn(p-1)-1 surgery on a positive torus knot of type (p, pn+1). We prove that E(2,n) does not carry tight contact structures for any n, while E(p,n) carries tight contact structures for any n and any odd p. In part…
Models predict probabilities of causation from limited data.
problem Estimating probabilities of causation requires unreliable or impractical experimental and observational data.
method Proposed Exact-MLP and Mask-MLP models trained on reliable subpopulations.
result Models achieve average MAEs of roughly 0.03, reducing MAE by 80%.
RP method improves noisy label classification with CNN, achieving 0.46 error across all MNIST digits.
problem Noisy label binary classification with mislabeled examples.
method Rank Pruning (RP) for estimating noise rates and improving classification.
result RP achieves state-of-the-art performance in noisy label classification.
A neural framework corrects bias in estimating individual treatment effects.
problem Estimating individual treatment effects from observational data.
method An anchored neural architecture and precision-corrected intersection-bound inference.
result Corrected bias and maintained nominal coverage in high-dimensional settings.
Introduces three types of partial bihamiltonian structures.
problem None explicitly stated; focuses on definitions and geometrical objects.
method Definition and study of geometrical objects linked with partial bihamiltonian structures.
result Examples of partial bihamiltonian structures in finite and infinite dimensions.
In this paper, we prove that, up to similarity, there are only two minimal hypersurfaces in R n + 2 \mathbb{R}^{n+2} R n + 2 that are asymptotic to a Simons cone, i.e. the minimal cone over the minimal hypersurface p n S p × n − p n S n − p \sqrt{\frac pn}\mathbb{S}^p\times \sqrt{\frac{n-p}n} \mathbb{S}^{n-p} n p S p × n n − p S n − p of S n + 1 \mathbb{S}^{n+1} S n + 1
The paper examines percentiles of non-identical random variables and provides non-asymptotic bounds.
problem Investigating percentiles of independent but non-identical random variables.
method Analyzing the 100 ( 1 − p ) 100(1-p) 100 ( 1 − p ) %-th percentile X ( p n ) X^{(pn)} X ( p n ) for a wide class of distributions. result Discovering a connection between the median and the harmonic mean of standard deviations for certain distributions.
The study characterizes and proves properties of 3D Poisson quasi-Nijenhuis manifolds.
problem Characterizing and understanding 3D Poisson quasi-Nijenhuis manifolds.
method Characterization through deformation and application of Haantjes structures.
result Every 3D Poisson quasi-Nijenhuis manifold is a Haantjes manifold.
This research explains how Batch Normalization improves neural networks through theoretical analysis.
problem Understanding the impact of Batch Normalization on neural network training and generalization.
method Using a basic neural network block, the study analyzes Batch Normalization by decomposing it into population normalization and gamma decay.
result Batch Normalization acts as an implicit regularizer, decomposable into explicit components that affect learning dynamics and generalization.
We continue our study of the knot Floer homology invariants of cable knots. For large |n|, we prove that many of the filtered subcomplexes in the knot Floer homology filtration associated to the (p,pn+1) cable of a knot, K, are isomorphic to those of K. This result allows us to obtain information about the behavior of …
Generates realistic person images for re-id, overcoming pose variations.
problem Lack of cross-view paired training data and pose variations in person re-identification.
method Pose-normalization GAN (PN-GAN) for generating images conditioned on pose.
result Synthesized images enable learning invariant features free of pose variations.
Model predicts future term connections in biomedical research.
problem Capturing temporal dynamics and unobserved connections in biomedical term relationships.
method Variational inference model for positive-unlabeled learning on dynamic graphs.
result Model effectively predicts term relationships in real-world datasets.
This paper is devoted to the study of the knot Floer homology groups HFK(S^3,K_{2,n}), where K_{2,n} denotes the (2,n) cable of an arbitrary knot, K. It is shown that for sufficiently large |n|, the Floer homology of the cabled knot depends only on the filtered chain homotopy type of CFK(K). A precise formula for this …
In this paper, we study the Khovanov homology of cable links. We first estimate the maximal homological degree term of the Khovanov homology of the ( 2 k + 1 2k+1 2 k + 1 , ( 2 k + 1 ) n (2k+1)n ( 2 k + 1 ) n )-torus link and give a lower bound of its homological thickness. Specifically, we show that the homological thickness of the ( 2 k + 1 2k+1 2 k + 1 , ( 2 k + 1 ) n (2k+1)n ( 2 k + 1 ) n )-torus li…
This paper improves privacy accounting in decentralized FL using f-Differential Privacy.
problem Challenges in accurately quantifying privacy budget in decentralized FL.
method Develops two new f-DP-based accounting methods for decentralized FL.
result Yields tighter (ε,δ) bounds and improved utility compared to existing methods.
DEDPUL improves PU learning by estimating proportions and classifying unlabeled data.
problem Analog to supervised binary classification with only positive samples clean and unlabeled mixtures of positive and negative.
method Applies a post-processing procedure to any classifier trained to distinguish positive and unlabeled data, estimating proportions alongside classification.
result Outperforms state-of-the-art in both proportion estimation and PU classification.
Improved few-shot learning with unlabeled data using random walks.
problem Few-shot learning with limited labeled data.
method Prototypical Random Walk Networks (PRWN) with semi-supervised loss.
result Significant performance improvements in most benchmarks.
Evaluation often aims to reduce the correctness or error characteristics of a system down to a single number, but that always involves trade-offs. Another way of dealing with this is to quote two numbers, such as Recall and Precision, or Sensitivity and Specificity. But it can also be useful to see more than this, and …
We consider parallel submanifolds M M M of a Riemannian symmetric space N N N and study the question whether M M M is extrinsically homogeneous in N N N \,, i.e.\ whether there exists a subgroup of the isometry group of N N N which acts transitively on M M M \,. First, given a "2-jet" ( W , b ) (W,b) ( W , b ) at some point p ∈ N p\in N p ∈ N (i.e. $W\subset T…
New algorithm for faster support recovery in quadratic logistic regression.
problem Support recovery in quadratic logistic regression with sparse non-linear terms.
method Identify weak support via novel non-linear correlation test, then perform standard logistic regression on chosen variables.
result Support recovery in sub-quadratic time, achieving significant computational gains.
New algorithm detects communities near KS threshold with optimal rate, even in noisy conditions.
problem Community detection in symmetric stochastic block models with noisy data.
method Polynomial-time algorithm using Sum-of-Squares framework and robust majority voting.
result Achieves minimax-optimal misclassification rate near Kesten-Stigum threshold, even with node corruption.
The paper explores Cholesky decompositions for symmetric matrices and their geometric properties.
problem Understanding the structure and properties of symmetric matrices through Cholesky decompositions.
method Introducing cones of symmetric matrices, proving Cholesky-type factorizations, and showing geometric properties.
result Each symmetric matrix admits an uncountable family of Cholesky-type factorizations, and these cones are isometric Riemannian manifolds.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
problem Adapting models to unseen tasks efficiently and accurately.
method Black-box, metric-based, layered, and Bayesian approaches.
result Meta-learning enhances model generalization and adaptation to unseen tasks.
Meta-learning improves neural networks by adapting learning algorithms.
problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.
metric-learn simplifies metric learning in Python.
problem Performing distance metric learning efficiently.
method Unified scikit-learn compatible interface for supervised and weakly-supervised metric learning.
result Unified interface for cross-validation and model selection.
Meta-learning speeds up learning new tasks.
problem Designing and improving machine learning pipelines.
method Observing and learning from different machine learning approaches.
result Learning new tasks much faster than traditional methods.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
Machine learning models adapt to motor learning but face challenges.
problem Adapting machine learning to handle motor variability and differentiate new movements from known ones.
method Parameter adaptation, transfer and meta-learning, reinforcement learning.
result Challenges in applying machine learning models for motor learning support systems.
Dropout learning is analyzed as ensemble learning to prevent overfitting.
problem Overfitting in deep learning models.
method Dropout learning ignores some inputs and hidden units with a probability, p, and combines them with the learned network.
result Combining neglected hidden units with the learned network can be seen as ensemble learning.
Optimal learning paths designed for E-learning systems using reinforcement learning.
problem Designing optimal learning paths for E-learning systems.
method Developed a hierarchical skill model and a proficiency level model, applied reinforcement learning to find the optimal learning strategy.
result Demonstrated the effectiveness of the proposed framework via numerical experiments.
New theory improves deep learning performance without statistical assumptions.
problem Improving deep learning performance without statistical assumptions.
method Measure-theoretic theory for machine learning, derived regularization method.
result New regularization method outperforms previous methods in various datasets.
Dex improves reinforcement learning by solving complex environments incrementally.
problem Training reinforcement learning agents for complex, ever-changing environments.
method Incremental learning approach, using optimal weights from simpler environments.
result Incremental learning yields superior performance across multiple Dex environments.
HGAIL learns policies without expert demonstrations.
problem Lack of expert demonstrations in imitation learning.
method Combines hindsight and GAIL to learn policies.
result Comparable performance to current methods, with curriculum learning.
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
problem Challenging reinforcement learning problems in continuous control.
method Learned state abstraction to transform continuous state-space into discrete.
result Tabular Q-Learning with learned abstractions achieves efficient learning in unseen tasks.
Unsupervised meta-learning speeds up reinforcement learning tasks.
problem Efficiently solving new reinforcement learning tasks.
method Formulating unsupervised meta-reinforcement learning and using mutual information for task proposals.
result Unsupervised meta-reinforcement learning effectively acquires accelerated procedures without manual task design.
Pymc-learn simplifies probabilistic machine learning for non-specialists.
problem Making probabilistic machine learning accessible to non-experts.
method Inspired by scikit-learn, Pymc-learn provides a high-level language for probabilistic models.
result Pymc-learn brings probabilistic machine learning to non-specialists with ease, performance, and flexibility.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
AI learns to learn sequentially without forgetting.
problem Preventing catastrophic forgetting in machine learning models.
method Meta-learning a neuromodulatory activation-gating function to control selective activation in deep neural networks.
result State-of-the-art continual learning performance with 600 classes (9,000 updates).
Paper discusses flaws in traditional RL for lifelong learning.
problem Traditional RL fails to model lifelong learning systems.
method Simplified prototype of lifelong RL system.
result Insights into lifelong RL, showing traditional RL's limitations.