Shielded LMC samples from non-convex spaces with repulsive drift.
problem Sampling from non-convex spaces with convex holes.
method Combining adaptive temperature and repulsive drift.
result Advantages over unconstrained sampling in constrained spaces.
Study identifies stable configurations of intertwined threads with repulsive interactions.
problem Stable configurations of entangled systems with repulsive interactions.
method Analysis of steepest descent flow of an energy functional.
result Existence and uniqueness of stable configuration of two layers drifting apart at t1/3 rate. Study shows global invertibility in nonlinear elasticity with vanishing self-repulsion term.
problem Global invertibility in nonlinear elasticity with a vanishing nonlocal self-repulsion term.
method Proves global invertibility in the Γ-limit of elastic energy with a vanishing nonlocal self-repulsion term. result Global invertibility can be obtained in the Γ-limit of the elastic energy with a vanishing nonlocal self-repulsion term. Repulsive ensembles improve uncertainty estimates in PINNs for differential equations.
problem Improving uncertainty estimates in PINNs for differential equations.
method Employing repulsive ensembles (RE-PINN) with a repulsive term in the loss function.
result Repulsive ensembles produce more accurate uncertainty estimates and higher sample diversity.
Neighbor embeddings balance attraction and repulsion to visualize data.
problem Visualizing high-dimensional datasets with trade-offs between continuous and discrete structures.
method Neighbor embeddings combine attractive and repulsive forces to visualize data.
result Changing the exaggeration parameter in t-SNE yields a spectrum of embeddings with a trade-off between continuous and discrete structures.
Introduce a variance-weighted batch distribution for diverse sampling in diffusion models.
problem Independent sampling in diffusion models.
method Introduce a variance-weighted batch distribution.
result Sampler with a transparent probabilistic target.
ARS visualization improves t-SNE dynamics with tunable attraction and repulsion.
problem Improve data visualization techniques for complex data sets.
method ARS framework based on t-SNE dynamics with normalized interactions and tunable kernels.
result ARS visualization provides better control over cluster tightness and spacing.
Repulsive deep ensembles improve diversity and Bayesian inference.
problem Challenges in maintaining diversity among ensemble members trained independently.
method Introducing a repulsive term in the update rule of deep ensembles.
result Training dynamics of repulsive ensembles follow a Wasserstein gradient flow of KL divergence with the true posterior.
Computer experiments reveal complex knots that don't simplify.
problem Understanding the dynamics of complex knots under self-repulsion.
method Computer simulations of knot theory, focusing on rational knots and tangles.
result Discovered hard unknots and complexified knots that do not reduce to simpler forms under self-repulsion.
New method improves sample diversity and efficiency from complex distributions.
problem Sampling from intractable un-normalized distributions with high auto-correlation.
method Stein self-repulsive dynamics using a repulsive force to push samples away from past trajectories.
result Significantly decreases auto-correlation and increases effective sample size.
FoRDE uses input gradients to improve neural network ensembles.
problem Improving neural network ensembles for robustness and accuracy.
method Proposes FoRDE, an ensemble learning method based on ParVI, which repels function space by input gradients.
result FoRDE significantly outperforms DEs and other ensemble methods in accuracy and calibration.
This work shows dimension regularization can replace skip-gram negative sampling for graph embeddings, improving efficiency and performance.
problem Efficiently enforcing dissimilarity among node embeddings in graph learning.
method Dimension regularization as an alternative to skip-gram negative sampling.
result Dimension regularization is a more efficient approach to enforcing dissimilarity in graph embeddings.
Paper improves particle variational inference by optimizing generalization error bound.
problem Improving the diversity of models in particle variational inference to enhance generalization.
method Develops a new second-order Jensen inequality with a repulsion term based on the loss function, leading to a tighter generalization error bound.
result The proposed PVI optimizes the generalization error bound directly, improving performance compared to existing methods.
New approach improves multi-head attention by making heads less similar.
problem Multi-head attention can lead to similar features, reducing model expressiveness.
method Proposes a non-parametric approach using Bayesian techniques to make heads repel each other.
result Improves feature diversity, leading to better representations and performance.
Research examines correlations of complex logarithms of lattice points, showing level repulsion and Poissonian behavior.
problem Analyzing correlations of complex logarithms of lattice points.
method Proving existence of pair correlation functions and examining behavior at various scalings.
result Level repulsion observed at linear scaling, Poissonian behavior at sublinear scalings.
Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. F…
We study the performance of the euro/Swiss franc exchange rate in the extraordinary period from September 6, 2011 and January 15, 2015 when the Swiss National Bank enforced a minimum exchange rate of 1.20 Swiss francs per euro. Based on the analogy between Brownian motion in finance and physics, the first-order effect …
RePULSe improves language model alignment by reducing undesired outputs without sacrificing overall performance.
problem Aligning language models with human preferences while minimizing undesired outputs.
method Integrates probabilistic inference into RL training to reduce undesired outputs.
result RePULSe achieves a better balance between expected reward and undesired output probability.
The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that such repulsive sampling schemes lowers the variance of the gradient est…
This paper introduces repulsive Monte Carlo methods for computing the sliced Wasserstein distance.
problem Computing the integral of a function on the unit sphere using Monte Carlo methods.
method The approach involves using determinantal point processes and repelled point processes to create quadratures for the sliced Wasserstein distance.
result The UnifOrtho estimator is recommended for the computation of the sliced Wasserstein distance in large dimensions.
New algorithm detects anomalies by forcing samples to displace mass in low-density regions.
problem Detecting anomalies in datasets.
method Mass Repulsing Optimal Transport (MROT) approach.
result Our algorithm improves anomaly detection over existing methods.
We consider the problem of diversity enhancing clustering, i.e, developing clustering methods which produce clusters that favour diversity with respect to a set of protected attributes such as race, sex, age, etc. In the context of fair clustering, diversity plays a major role when fairness is understood as demographic…
New Gaussian DPP model reveals directionality in data.
problem Negative dependence in data modeling.
method Investigation of Gaussian Determinantal Processes (GDPs) with parametric modulation.
result Parameter modulation introduces directionality in repulsion structure, affecting dependency.
We propose a unifying view of two different Bayesian inference algorithms, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) and Stein Variational Gradient Descent (SVGD), leading to improved and efficient novel sampling schemes. We show that SVGD combined with a noise term can be framed as a multiple chain SG-MCM…
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure…
A new model improves clustering by reducing redundancy in mixture of local EPCAs.
problem Redundancy in traditional mixture models causes ambiguity in clustering.
method Introduced a repulsiveness-encouraging prior and a DPP for diversity in DEPCAM model.
result The method reduces model redundancy and improves clustering performance.
The study examines correlations of logarithms of integers at different scalings.
problem Analyzing pair correlations of logarithms of integers at various scalings.
method Examined correlations of logarithms of positive integers at different scalings, proving the existence of pair correlation functions.
result Level repulsion at linear scaling, total loss of mass at superlinear scalings, and Poissonian behavior at sublinear scalings.
The paper proves a Lojasiewicz inequality for maps from the 2-sphere to itself.
problem Analyzing maps from the 2-sphere to itself using Lojasiewicz inequalities.
method Using Lojasiewicz-Simon inequalities and Topping's repulsion estimates, along with a bubble-tree induction argument.
result Polynomial convergence of weak solutions of harmonic map flow on compact domains.
Feature normalization prevents collapse in non-contrastive learning dynamics.
problem Non-contrastive learning can collapse into a single point due to lack of repulsive force.
method Extended previous theory based on L2 loss to cosine loss, considering feature normalization.
result Cosine loss induces stable equilibrium, preventing collapse even with insufficient repulsive force.
Paper proposes ARB-Loss to improve classification precision in imbalanced datasets.
problem Improving classification precision on minor classes in imbalanced datasets.
method Introduces Attraction-Repulsion-Balanced Loss (ARB-Loss) to balance gradients across different classes.
result ARB-Loss achieves state-of-the-art performance with one-stage training.
Determinantal point processes (DPPs) are random point processes well-suited for modeling repulsion. In machine learning, the focus of DPP-based models has been on diverse subset selection from a discrete and finite base set. This discrete setting admits an efficient sampling algorithm based on the eigendecomposition of…
Study on capillarity minimizers with nonlocal repulsion and gravity, proving existence and nonexistence.
problem Minimizing an energy functional with capillarity, nonlocal repulsion, and gravity.
method Quantitative isoperimetric inequalities applied to capillarity problem in a half-space.
result Existence and nonexistence of minimizers for various nonlocal kernels and masses.
This review covers learning under concept drift, including detection, understanding, and adaptation.
problem Unforeseeable changes in data distribution over time impact machine learning performance.
method Reviews and analyzes methodologies and techniques for concept drift detection, understanding, and adaptation.
result Establishes a framework for learning under concept drift with three main components.
New framework for detecting data drift in continuous time.
problem Drift in data distribution over time.
method Probability theoretical framework for continuous time drift.
result New efficient drift detection method and decomposition of data.
Identifies features most relevant to concept drift in data.
problem Identifying features most relevant to concept drift.
method Distinguishing between drift inducing and faithfully drifting features; deriving minimal subsets of features to characterize drift.
result Derives a detection algorithm for concept drift.
Determinantal point processes (DPPs) enable the modeling of repulsion: they provide diverse sets of points. The repulsion is encoded in a kernel K that can be seen as a matrix storing the similarity between points. The diversity comes from the fact that the inclusion probability of a subset is equal to the determinan…
The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this work, we propose clustering-oriented representation learning (COREL) as an altern…
New method detects when models influence their own drift in real-time data streams.
problem Models can induce concept drift in real-time data streams.
method CheckerBoard Performative Drift Detection (CB-PDD)
result CB-PDD effectively detects performative drift in real-time data streams.
This research identifies flaws in drift detection methods and creates adversarial data streams to exploit them.
problem The challenge of detecting data distribution changes (drift) in real-time systems.
method Developed adversarial data streams to show weaknesses in existing drift detection schemes.
result Demonstrated that common drift detection methods can be fooled by adversarial data streams.
Image partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments, or equivalently to detect closed contours. Most prior work either requires seeds, one per segment; or a threshold; or formulates the task as multicut / correlation clustering, an NP-hard problem. Here, we …
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods. However, we observed th…
A new drift detection method based on autoregressive models.
problem Concept drift in real-world data leads to decreased model performance.
method Autoregressive based drift detection method (ADDM).
result ADDM outperforms state-of-the-art drift detection methods.
Adaptive sampling detects local concept drift with limited labels.
problem Detecting local concept drift in dynamic environments with scarce labels.
method Combines residual-based exploration and exploitation with EWMA monitoring.
result Superior performance in label efficiency and drift detection accuracy.
Algorithm detects concept drift and adapts models in streaming data.
problem Concept drift in streaming data renders models inaccurate.
method Adaptive learning algorithm that detects drifts and reacts to them.
result Risk competitive to an algorithm with perfect drift knowledge.
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches have been developed in literature to deal with the problem of drift handling an…
Enhances contrastive learning for better representation learning on wild images.
problem Binary partition of views from same and different instances limits CL's performance.
method Doubly Contrastive Learning (CACR) with contrastive attraction and repulsion.
result CACR improves performance and robustness on wild image datasets.
Classifies polynomial growth solutions to drift-harmonic equations on asymptotically paraboloidal manifolds.
problem Classifying polynomial growth solutions to drift-harmonic equations on specific types of manifolds.
method Inductive argument that alternates between constructing and asymptotically controlling drift-harmonic functions.
result All drift-harmonic functions with polynomial growth asymptotically separate variables and dimensions of spaces are computed.
Learning of low dimensional structure in multidimensional data is a canonical problem in machine learning. One common approach is to suppose that the observed data are close to a lower-dimensional smooth manifold. There are a rich variety of manifold learning methods available, which allow mapping of data points to the…