We study global fixed points for actions of Coxeter groups on nonpositively curved singular spaces. In particular, we consider property FA_n, an analogue of Serre's property FA for actions on CAT(0) complexes. Property FA_n has implications for irreducible representations and complex of groups decompositions. In this p…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Property FA”
In this paper we consider Property (FA) for lattices in SU(2,1). First, we prove that SU(2,1;O_3) has Property (FA). We then prove that the arithmetic lattices in SU(2,1) of second type arising from congruence subgroups studied by Rapoport--Zink and Rogawski cannot split as a nontrivial free product with amalgamation; …
Non-isomorphic groups with similar profinite completions found.
problem Finding non-isomorphic groups with similar profinite completions.
method Exhibited infinitely many pairs of non-isomorphic groups with specific properties.
result Groups with Property FA and non-trivial actions on trees have isomorphic profinite completions.
The study shows that several properties are not profinite invariants.
problem Determining which properties are profinite invariants.
method Combining Rips constructions and iterated group-theoretic Dehn filling on hyperbolic virtually special groups.
result Several properties (stable commutator length, quasimorphisms, property NL, property FW, property FA, and non-abelian free subgroups) are not profinite invariants.
We study codimension one (transversally oriented) foliations $\fa$ on oriented closed manifolds having non-empty compact singular set $\sing(\fa)$ which is locally defined by Bott-Morse functions. We prove that if the transverse type of $\fa$ at each singular point is a center and $\fa$ has a compact leaf with fini…
ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mappingcs.LG
ICAM creates interpretable feature attribution maps for brain images.
problem Challenges in predicting class relevance from brain images due to heterogeneity and background variation.
method A VAE-GAN framework for disentangling class relevance from background features.
result FA maps generated by ICAM outperform baseline methods and support phenotype variation exploration.
FA-HMC improves Bayesian federated learning with rigorous guarantees.
problem Parameter estimation and uncertainty quantification in non-iid distributed data.
method Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC) with convergence guarantees.
result FA-HMC achieves better convergence and communication efficiency than existing methods.
We prove that random groups in the Gromov density model, at any density, satisfy property (FA), i.e. they do not act non-trivially on trees. This implies that their Gromov boundaries, defined at density less than 1/2, are Menger curves.
Study improves understanding and performance of FA learning rules in neural networks.
problem Lack of theoretical understanding and limited applications of Feedback Alignment (FA) methods.
method Introduces a unified framework linking synaptic weight changes to implicit regularization, providing convergence conditions and empirical evidence.
result Better alignment can enhance FA performance on complex multi-class tasks.
We prove some general results about quasi-actions on trees and define Property (QFA), which is analogous to Serre's Property (FA), but in the coarse setting. This property is shown to hold for a class of groups, including for . We also give a way of thinking about Property (QFA) by breaking it down …
Random Feedback Alignment helps solve low-rank matrix factorization problems.
problem Solving low-rank matrix factorization problems efficiently.
method Random Feedback Alignment (FA) as a bio-plausible alternative to gradient descent.
result FA converges to the optimal solution when the rank of the matrix is at least the rank of the input matrix.
Proposes a robust factor analysis for matrix data.
problem Robust factor analysis for matrix data with heavy-tailed or contaminated data.
method Bilinear factor analysis based on the matrix-variate distribution.
result Significantly higher breakdown point than traditional methods.
Comparing the performance of FA, DFA and DMA using different synthetic long-range correlated time seriesphysics.data-an
Notwithstanding the significant efforts to develop estimators of long-range correlations (LRC) and to compare their performance, no clear consensus exists on what is the best method and under which conditions. In addition, synthetic tests suggest that the performance of LRC estimators varies when using different genera…
FACTM combines FA with correlated topic modeling for structured data integration.
problem Integrating structured data modalities like text and single cell sequencing.
method Bayesian FACTM model combining FA and correlated topic modeling with variational inference.
result FACTM outperforms other methods in identifying clusters in structured data and integrating them with simple modalities.
Highly accurate interval forecasting of a stock price index is fundamental to successfully making a profit when making investment decisions, by providing a range of values rather than a point estimate. In this study, we investigate the possibility of forecasting an interval-valued stock price index series over short an…
FA-LD algorithm improves uncertainty quantification and mean predictions in federated learning.
problem Uncertainty quantification and mean predictions in federated learning with distributed clients.
method FA-LD algorithm for strongly log-concave distributions with non-i.i.d data, considering general models.
result The FA-LD algorithm provides theoretical guarantees for convergence and optimal noise injection.
We extend our previous study of scaling range properties done for detrended fluctuation analysis (DFA) \cite{former_paper} to other techniques of fluctuation analysis (FA). The new technique called Modified Detrended Moving Average Analysis (MDMA) is introduced and its scaling range properties are examined and compared…
Within machine learning, the subfield of Neural Architecture Search (NAS) has recently garnered research attention due to its ability to improve upon human-designed models. However, the computational requirements for finding an exact solution to this problem are often intractable, and the design of the search space sti…
Optimal privacy and accuracy in distributed mean estimation with compression.
problem Achieving optimal accuracy under privacy and communication constraints.
method Compression to reduce communication while maintaining privacy and accuracy.
result Achieves optimal error with significantly reduced communication.
Compressed Federated Distillation reduces communication in federated learning.
problem Communication constraints in Federated Learning.
method Compressed Federated Distillation (CFD) leverages soft labels and quantization techniques.
result Reduces communication by more than 4 orders of magnitude compared to Federated Averaging.
Researchers study fairness-accuracy tradeoffs in predictive models for multiple groups.
problem Understanding the tradeoff between fairness and accuracy in models serving multiple demographic groups.
method Characterizing the fairness-accuracy (FA) Pareto frontier, approximating it from limited data, and bounding the worst-case gap.
result Derivation of worst-case-optimal estimators and uniform finite-sample bounds for the entire FA frontier.
The accurate diagnosis and assessment of neurodegenerative disease and traumatic brain injuries (TBI) remain open challenges. Both cause cognitive and functional deficits due to focal axonal swellings (FAS), but it is difficult to deliver a prognosis due to our limited ability to assess damaged neurons at a cellular le…
Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.
problem Understanding how different learning rules affect feature and prediction dynamics in deep neural networks.
method Analysis of infinite-width deep networks trained with gradient descent and various learning rules.
result The evolution of the output function is governed by an effective neural tangent kernel (eNTK), which varies depending on the learning rule and training regime.
Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networkscs.LG
FA algorithm provides convergence guarantees for deep linear networks.
problem Training efficiency and convergence of deep neural networks.
method Theoretical analysis of Feedback Alignment (FA) algorithm for deep linear networks.
result Certain initializations lead to implicit anti-regularization, affecting learning effectiveness.
Latent variable models can be used to probabilistically "fill-in" missing data entries. The variational autoencoder architecture (Kingma and Welling, 2014; Rezende et al., 2014) includes a "recognition" or "encoder" network that infers the latent variables given the data variables. However, it is not clear how to handl…
We construct examples of finitely generated groups L that have non-trivial actions on -trees but which cannot act, without fixing a vertex, on any simplicial tree. Moreover, any finitely presented group mapping onto L does have a fixed point-free action on some simplicial tree.
Frame Averaging makes neural networks invariant or equivariant to new symmetries.
problem Designing neural networks that respect symmetries while being expressive and efficient.
method Introduces Frame Averaging (FA) as a systematic framework to adapt architectures to become invariant or equivariant to new symmetries.
result Frame Averaging guarantees exact invariance or equivariance while being simpler to compute than full group averaging.
The Bayesian approach to feature extraction, known as factor analysis (FA), has been widely studied in machine learning to obtain a latent representation of the data. An adequate selection of the probabilities and priors of these bayesian models allows the model to better adapt to the data nature (i.e. heterogeneity, s…
Inference of Sparse Networks with Unobserved Variables. Application to Gene Regulatory Networksstat.ML
Networks are a unifying framework for modeling complex systems and network inference problems are frequently encountered in many fields. Here, I develop and apply a generative approach to network inference (RCweb) for the case when the network is sparse and the latent (not observed) variables affect the observed ones. …
Adjoint sampler targets infinite-dimensional function spaces for efficient sampling.
problem Limited theory and algorithms for sampling infinite-dimensional function spaces.
method Adjoint Sampler for infinite-dimensional function spaces based on stochastic maximum principle.
result FAS achieves superior performance in synthetic and real systems.
Neuro-Causal Factor Analysisstat.ML
NCFA uses deep learning and causal discovery to analyze complex data.
problem Analyzing complex, interdependent data with causal relationships.
method NCFA combines latent causal discovery and variational autoencoders.
result NCFA outperforms standard VAEs in sparsity, complexity, and causal interpretability.
Some high-dimensional data.sets can be modelled by assuming that there are many different linear constraints, each of which is Frequently Approximately Satisfied (FAS) by the data. The probability of a data vector under the model is then proportional to the product of the probabilities of its constraint violations. We …
The front-end factor analysis (FEFA), an extension of principal component analysis (PPCA) tailored to be used with Gaussian mixture models (GMMs), is currently the prevalent approach to extract compact utterance-level features (i-vectors) for automatic speaker verification (ASV) systems. Little research has been conduc…
We analyze symmetries in overparametrized neural networks using a mean-field approach.
problem Understanding symmetries in overparametrized neural networks under data symmetry.
method Developed a Mean-Field view of learning dynamics for overparametrized neural networks under data symmetry.
result Symmetric models under data symmetry converge to the space of invariant laws and minimize population risk.
The backpropagation of error algorithm (BP) is impossible to implement in a real brain. The recent success of deep networks in machine learning and AI, however, has inspired proposals for understanding how the brain might learn across multiple layers, and hence how it might approximate BP. As of yet, none of these prop…
The backpropagation (BP) algorithm is often thought to be biologically implausible in the brain. One of the main reasons is that BP requires symmetric weight matrices in the feedforward and feedback pathways. To address this "weight transport problem" (Grossberg, 1987), two more biologically plausible algorithms, propo…
The Lethal Dose Conjecture limits how much poisoned data can be tolerated.
problem Limiting the impact of poisoned data in machine learning models.
method Theoretical analysis and provable defenses (DPA, FA) based on majority voting.
result DPA and FA are asymptotically optimal defenses against data poisoning.
This paper uses PCA and FA for feature selection in credit rating.
problem Selecting important features for credit rating prediction.
method Principal Component Analysis and Factor Analysis.
result Factor Analysis reduces feature set significantly without losing much accuracy.
Minimal submanifolds in octonionic hyperbolic spaces have large volume.
problem Characterizing minimal submanifolds in locally symmetric spaces.
method Analyzing higher expansion properties and volume constraints.
result Codimension two minimal submanifolds have at least linear volume in the ambient space.
A nonparametric Bayesian extension of Factor Analysis (FA) is proposed where observed data is modeled as a linear superposition, , of a potentially infinite number of hidden factors, . The Indian Buffet Process (IBP) is used as a prior on to incorporate sparsity and to …
Objective: Multimodal measurements of the same phenomena provide complementary information and highlight different perspectives, albeit each with their own limitations. A focus on a single modality may lead to incorrect inferences, which is especially important when a studied phenomenon is a disease. In this paper, we …
Feedback alignment methods need to be evaluated for accuracy and gradient cosine similarity.
problem Evaluating feedback alignment methods
method Proposed diagnostic evaluation protocol
result Identified silent failures in standard reporting pair
Study contact 3-manifolds using sub-Riemannian geometry, proving new properties of their Lipschitz homotopy groups.
problem Characterize the Lipschitz homotopy groups of contact 3-manifolds.
method Sub-Riemannian geometry, geometric measure theory, biLipschitz equivalence, purely unrectifiable sets.
result Contact 3-manifolds are spaces with uncountably generated first homotopy groups.
Because tensor data appear more and more frequently in various scientific researches and real-world applications, analyzing the relationship between tensor features and the univariate outcome becomes an elementary task in many fields. To solve this task, we propose \underline{Fa}st \underline{S}parse \underline{T}ensor…
Diffusion magnetic resonance imaging (dMRI) and tractography provide means to study the anatomical structures within the white matter of the brain. When studying tractography data across subjects, it is usually necessary to align, i.e. to register, tractographies together. This registration step is most often performed…
A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical Modelsstat.ML
Estimating multiple sparse Gaussian Graphical Models (sGGMs) jointly for many related tasks (large ) under a high-dimensional (large ) situation is an important task. Most previous studies for the joint estimation of multiple sGGMs rely on penalized log-likelihood estimators that involve expensive and difficult n…
A new method quickly identifies key variables and interactions.
problem Identifying key variables and interactions in high-dimensional data.
method Kernel trick for sparse orthogonal decomposition in O(# covariates) time.
result Outperforms existing methods for large, high-dimensional data sets.
VISTA learns causal structures by integrating local subgraphs, improving accuracy and efficiency.
problem Efficiently learning causal structures from high-dimensional observational data.
method VISTA decomposes the global causal structure learning problem into local subgraphs based on Markov Blankets, integrating them via a weighted voting mechanism.
result VISTA achieves notable improvements in accuracy and efficiency over existing methods.