The paper uses persistent homology to estimate recurrence times in multi-variate time series.
problem Estimating recurrence times in multi-variate time series with different cyclic behaviors.
method Persistent homology framework with three specialized methods.
result Validated methods on real-world data, including a new benchmark dataset.
Geometrical and appearance quality requirements set the limits of the current industrial performance in injection molding. To guarantee the product's quality, it is necessary to adjust the process settings in a closed loop. Those adjustments cannot rely on the final quality because a part takes days to be geometrically…
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.
In this paper we present a connection between two dynamical systems arising in entirely different contexts: one in signal processing and the other in biology. The first is the famous Iteratively Reweighted Least Squares (IRLS) algorithm used in compressed sensing and sparse recovery while the second is the dynamics of …
GraSP-RL uses graph neural networks to improve job shop scheduling.
problem Capturing machine-unit-job sequence relationships and managing state space growth.
method Graph neural networks for feature extraction, reinforcement learning for decision-making, decentralized optimization.
result GraSP-RL outperforms existing methods in minimizing makespan for complex production environments.
Proposes a method to enhance graph models by injecting unseen connections.
problem Enhancing graph models to utilize unseen connections.
method Parametric link injection layer to find and inject weak connections.
result Improves performance on node classification and link prediction tasks.
Bayesian models can be tricked into believing false data.
problem Vulnerability of Bayesian inference to data poisoning attacks.
method Developed attacks to manipulate Bayesian posterior through deletion and replication of data.
result Demonstrated that Bayesian inference can be steered to target distributions.
Training shapes the geometry of neural network feature maps, revealing local area magnification.
problem Understanding how training affects the geometric structure of neural network feature maps.
method Analyzing the Riemannian geometry induced by neural network feature maps at infinite width and after training.
result Training breaks the symmetry of the geometry induced by random neural network feature maps, magnifying local areas along decision boundaries.
TensorFI injects faults in TensorFlow programs to assess their reliability.
problem Ensuring reliability of machine learning systems in safety-critical domains.
method TensorFI is a flexible fault injection framework for TensorFlow applications.
result TensorFI evaluates the resilience of 12 ML programs, including autonomous vehicle DNNs.
Studies on massive open online courses (MOOCs) users discuss the existence of typical profiles and their impact on the learning process of the students. However defining the typical behaviors as well as classifying the users accordingly is a difficult task. In this paper we suggest two methods to model MOOC users behav…
Proposes a method for neural networks to learn causal relationships and humans to contest and modify them.
problem Neural networks learn relevant causal relationships unclearly and are black-box, making them hard to debug.
method Two-way interaction between neural networks and humans, allowing contestation and modification of causal graphs.
result Improves predictive performance up to 2.4x and produces smaller networks up to 7x compared to SOTA.
Anti-correlated noise improves machine learning model generalization.
problem Improving machine learning model generalization.
method Injecting anticorrelated noise into gradient descent steps.
result Anti-correlated noise leads to better model generalization than uncorrelated noise.
The safety and resilience of fully autonomous vehicles (AVs) are of significant concern, as exemplified by several headline-making accidents. While AV development today involves verification, validation, and testing, end-to-end assessment of AV systems under accidental faults in realistic driving scenarios has been lar…
Adversarial weight perturbations can inject backdoors into trained neural models.
problem Security risk of using publicly available trained models due to backdoors.
method Extended adversarial perturbations to model weights, using a composite loss and projected gradient descent.
result Adversarial weight perturbations can be successfully injected with very small changes, exposing security risks across various tasks.
This paper shows how integrating domain knowledge improves ML models for transprecision computing.
problem Improving ML models for transprecision computing with scarce or complex data.
method Injecting domain knowledge into neural networks through additional features, graph-based topology, and regularization schemes.
result ML models with domain knowledge outperform purely data-driven models by around 38%.
New method for certified unlearning reduces noise injection.
problem Achieving formal unlearning guarantees with adaptive noise calibration.
method Adaptive per-instance noise calibration based on individual data point sensitivities.
result Derivation of high-probability per-instance sensitivity bounds for ridge regression.
Paper proposes NeuroAttack to undermine SNNs security through bit-flips.
problem Security and reliability issues in SNNs.
method Cross-layer attack exploiting low-level reliability issues via adversarial input noise.
result Serious integrity threat to SNNs and DNNs.
We consider the design of prediction market mechanisms known as automated market makers. We show that we can design these mechanisms via the mold of \emph{exponential family distributions}, a popular and well-studied probability distribution template used in statistics. We give a full development of this relationship a…
Smart bin monitors predict medication adherence with high accuracy.
problem Predicting chronic medication adherence to improve healthcare efficiency.
method Machine learning models trained on IoT device data.
result High predictive performance (ROC AUC 0.86).
Survey discusses new ideas in geometric group theory and their applications.
problem Understanding geodesic metric spaces and their equivariant wall structures.
method Introduces and highlights the impact of injective metric spaces and cubical approximation theorem.
result Rich equivariant wall structures in various geodesic metric spaces.
Researchers describe isometric deformations of T-hedra and T-surfaces.
problem Understanding the isometric deformations of discrete and smooth T-surfaces.
method Synthetic and analytic descriptions of T-hedra and T-surfaces, providing parametrizations of isometric deformations.
result Explicit parametrization of isometric deformations of T-hedra and T-surfaces.
Paper introduces uncertainty injection for deep learning robust optimization.
problem Uncertainty in input data affects deep learning model performance in optimization problems.
method Uncertainty injection scheme for training deep learning models to produce robust solutions.
result Proposed scheme improves robustness of solutions in wireless communications applications.
New method for efficiently deleting data from ML models.
problem Efficiently removing data from trained ML models without retraining.
method Approximate deletion method for linear and logistic models.
result Significantly faster than existing methods, with linear time dependence on feature dimension.
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications including those where security is of great concern. Such popularity, however, may attr…
New Roman pipeline detects astronomical transients.
problem Automated detection of transients from Roman Space Telescope data.
method Machine learning model RuBR for distinguishing real from fake detections.
result Effective real-bogus classification in Roman era.
Injectivity of ReLU networks is characterized for generative models and inverse problems.
problem Injectivity in ReLU networks for generative models and inverse problems.
method Layerwise analysis, worst-case Lipschitz constants, differential topology, random projections.
result Global injectivity of ReLU networks requires expansivity between 3.4 and 10.5 for Gaussian matrices.
Classifies π1-injective maps between non-compact surfaces.
problem Characterizing maps with injective fundamental groups.
method Proper homotopy classification of maps.
result All π1-injective proper maps are classified. Positive injectivity radius for manifolds with Lie structure at infinity.
problem Injectivity radius positivity for manifolds with specific boundary conditions.
method Lie groupoids to prove injectivity radius positivity.
result Injectivity radius is positive for manifolds with Lie structure at infinity.
Geometric analysis improves noise injection in GANs.
problem Unclear mechanism of noise injection in GANs.
method Geometric framework based on Riemannian geometry.
result A new strategy for noise injection is devised.
The paper analyzes optimal dividend and capital injection strategies under time-inconsistent preferences.
problem Optimal dividend and capital injection strategies under time-inconsistent preferences.
method Diffusion risk model with general discount functions, weak equilibrium definition, HJB equation system.
result Explicit solutions and threshold types of optimal strategies derived under different discount functions.
A quasi-geodesic is Morse if and only if it is strongly contracting in injective spaces.
problem Characterizing Morse quasi-geodesics in injective spaces.
method Proving equivalence between Morse and strongly contracting quasi-geodesics.
result Injective metric spaces have the Morse local-to-global property and acylindrically hyperbolic groups with Morse elements.
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated adversarial images easily transfer between networks trained with the same strategy. Inspir…
This paper connects noise injection to Bayesian inference for neural networks, improving model uncertainty.
problem Improving the reliability and confidence of neural network predictions through uncertainty quantification.
method Introducing noise into neural network parameters during training and inference to estimate prediction uncertainty.
result The MCNI method outperforms baseline models in regression and classification tasks.
Compact theorem for minimal surfaces with lower injectivity radius.
problem Proving compactness of minimal surfaces with lower injectivity radius.
method Variant of Choi--Schoen compactness theorem, focusing on injectivity radius.
result Proved compactness theorem for minimal surfaces.
Lecture notes on group actions on injective spaces and Helly graphs.
problem Understanding group actions on specific metric spaces.
method Review of injective metric spaces and Helly graphs, elementary properties, constructions, and exercises.
result Presentation of various constructions of injective metric spaces and Helly graphs with interesting group actions.
Proves polynomial injectivity of Fubini-Study map for ample line bundles.
problem Injectivity of Fubini-Study map for ample line bundles.
method Polynomial injectivity proof with polynomial dependence on ample line bundle exponent.
result Quantitative version of injectivity proved, polynomial in ample line bundle exponent.
Lower bound on boundary injectivity radius for specific tubes.
problem Estimating the boundary injectivity radius of Margulis tubes.
method Using curvature bounds to derive a lower bound.
result A lower bound on the boundary injectivity radius is provided.
Reservoir subspace injection improves online ICA by preserving injected features.
problem Discarding injected features in top-n whitening can degrade performance. method Formalized reservoir subspace injection (RSI) and developed diagnostics (IER, SSO, ρ_x) to identify and mitigate the failure mode.
result RSI controller preserves passthrough retention, improving performance by up to 2.2 dB.
Injective and surjective neural operators for function spaces.
problem Tackles injective and surjective neural operators in function spaces.
method Combines prior work in ReLU and operator learning, uses Fredholm theory and Leray-Schauder degree theory.
result Injective and surjective neural operators are universal approximators and maintain their properties in finite-rank implementations.
The paper proves that certain spaces are injective and Helly graphs.
problem Understanding the structure of certain geometric and algebraic spaces.
method Building Helly graphs and injective metric spaces from lattices.
result The natural piecewise ℓ∞ metric on Euclidean buildings and Deligne complexes is injective. Smooths metrics on manifolds with curvature bounds and injectivity radius constraints.
problem Smooth metrics on manifolds with curvature and injectivity constraints.
method Bi-Lipschitz smoothing with controlled smoothing and volume lower bounds.
result Proves existence of smooth metrics with curvature bounds and injectivity radius constraints.
Nonuniform tubular neighborhoods of curves in Euclidean n-space are studied by using weighted distance functions and generalizing the normal exponential map. Different notions of injectivity radii are introduced to investigate singular but injective exponential maps. A generalization of the thickness formula is obtaine…
In this paper, we obtain two-sided bounds for the volumes of the Aloff-Wallach spaces W(p,q), compute maximal and minimal sectional curvature for the spaces W(n,n+1), and use this information to estimate the injectivity radii: We derive an upper bound for the injectivity radii of W(p,q) and a lower bound for the …
Injectivity of geodesic ray transform on specific Finsler manifolds proven.
problem Injectivity of geodesic ray transform on spherically symmetric reversible Finsler manifolds.
method Reduction to invertibility of generalized Abel transforms using angular Fourier series and Taylor expansions of geodesics.
result Injectivity of geodesic ray transform proven on specified Finsler manifolds.
The paper shows regularization can't always find all optimal solutions in constrained ML.
problem Finding the right balance between model accuracy and constraint satisfaction.
method Formal demonstration of the limitations of regularization-based approaches in non-convex cases.
result There are optimal solutions for constrained problems that do not correspond to any multiplier value.
Noise Injection probes deep learning dynamics during training phases.
problem Understanding the learning mechanism of deep neural networks.
method Noise Injection Nodes (NINs) are used to perturb DNN architectures without altering the optimization algorithm.
result Distinct training phases are observed based on the scale of injected noise.
Generalizes a soul-bound for noncompact Alexandrov spaces.
problem Finding a lower bound for injectivity radius in Alexandrov spaces.
method Introduces the soul of Alexandrov spaces and applies a generalized bound.
result Injectivity radius is at least πK⁻¹/² if not equal to the soul's.
Optimal control problem for firm cash flow with dividend and capital injection strategies.
problem Maximizing dividends while managing capital injections in a firm's cash flow.
method Proved two optimal strategies: mean-reverting dividends with capital injections or no injections until ruin.
result Optimal strategies are dichotomous: either mean-reverting dividends with injections or no injections.