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.
Sparse Bayesian Optimization (SEBO) finds interpretable configurations.
Entropy regularization improves sparse model discovery in federated learning.
DreamerV3 learns diverse tasks with a single configuration.
We propose a method for solving statistical mechanics problems defined on sparse graphs. It extracts a small Feedback Vertex Set (FVS) from the sparse graph, converting the sparse system to a much smaller system with many-body and dense interactions with an effective energy on every configuration of the FVS, then learn…
BONSAI optimizes parameters while respecting a default configuration, reducing unnecessary changes.
Campfire simplifies sparse training for CNNs, achieving high accuracy with minimal pruning.
Greedy algorithm performs well in online matching despite non-i.i.d. connections.
High entropy alloys (HEAs) have been increasingly attractive as promising next-generation materials due to their various excellent properties. It's necessary to essentially characterize the degree of chemical ordering and identify order-disorder transitions through efficient simulation and modeling of thermodynamics. I…
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without conne…
In this article, we consider the sparse tensor singular value decomposition, which aims for dimension reduction on high-dimensional high-order data with certain sparsity structure. A method named Sparse Tensor Alternating Thresholding for Singular Value Decomposition (STAT-SVD) is proposed. The proposed procedure featu…
Sparse random networks reduce communication in federated learning.
Sparse point observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.
Modern deep neural networks are typically highly overparameterized. Pruning techniques are able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic reallocation of non-zero parameters have emerged, allowing direct training of sparse networks without…
Standard compressive sensing results state that to exactly recover an s sparse signal in R^p, one requires O(s. log(p)) measurements. While this bound is extremely useful in practice, often real world signals are not only sparse, but also exhibit structure in the sparsity pattern. We focus on group-structured patterns …
3BASiL-TM decomposes LLMs into sparse and low-rank matrices for efficient compression.
NACs learn modular neural architectures without domain knowledge.
New scheme for sparse feature selection in networked data.
Generative model learns wireless channel distributions efficiently.
Entropy regularization improves interpretability of probabilistic clustering models.
A new method for training generative models with sparse supervision.
Proposes a robust 3D classification method for sparse point clouds.
This paper presents a spermwhale' localization architecture using jointly a bag-of-features (BoF) approach and machine learning framework. BoF methods are known, especially in computer vision, to produce from a collection of local features a global representation invariant to principal signal transformations. Our idea …
Computes fundamental groups of restricted configuration spaces.
We study the configuration space of equilateral and equiangular spatial hexagons for any bond angle by giving explicit expressions of all the possible shapes. We show that the chair configuration is isolated, whereas the boat configuration allows one-dimensional deformations which form a circle in the configuration spa…
DCRL learns causal relationships from mixed-type discrete data.
Study shows configuration spaces' homological dimension increases monotonically.
A new Bayesian model improves forecasting for intermittent demand.
Researchers create a model for surface point configurations.
Transformers exhibit sparse activation maps, reducing computational load and improving robustness.
Tripod configurations of plane curves, formed by certain triples of normal lines coinciding at a point, were introduced by Tabachnikov, who showed that closed convex curves possess at least two tripod configurations. Later, Kao and Wang established the existence of tripod configurations for closed locally c…
We study the Orchard relation for generic configurations of points in the plane (also called order types). We introduce infinitesimally-close points and analyse the relation of this notion with the Orchard relation. The second part of the paper deals with monochromatic configurations (for the Orchard relation). We give…
This paper extends homological stability results for configuration spaces of manifolds.
Proposes a thermodynamic work minimization framework for guiding generative models.
Quantum groups created from disk configuration space homologies.
We study configurations of immersed curves in surfaces and surfaces in 3-manifolds. Among other results, we show that primitive curves have only finitely many configurations which minimize the number of double points. We give examples of minimal configurations not realized by geodesics in any hyperbolic metric.
Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to produce a confident misclassification. To protect against this we devi…
A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters. Given a set of configurations and a large dataset randomly split into training and testing set, we study how to efficiently select the best configuration with approximately the highest testing accuracy when trained f…
A modern aircraft may require on the order of thousands of custom shims to fill gaps between structural components in the airframe that arise due to manufacturing tolerances adding up across large structures. These shims are necessary to eliminate gaps, maintain structural performance, and minimize pull-down forces req…
Study orders of canonical bundles over graph configuration spaces.
Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption. We propose Monte Carlo methods to quantize the weights and activations of pre-trained neural networks without any re-training. By performing importance sampling we obtain quantiz…
Solves Plateau-Douglas problem for singular configurations in general metric spaces.
Ensuring that all supposedly valid configurations of a software product line (SPL) lead to well-formed and acceptable products is challenging since it is most of the time impractical to enumerate and test all individual products of an SPL. Machine learning classifiers have been recently used to predict the acceptabilit…
Study on disk configurations in strips shows stability patterns.
Study maps surface configurations to Heisenberg homologies for mapping class groups.
Sharp upper bound for quasi polynomial degree of manifold configuration spaces.
We prove a conjecture of Crapo and Penne which characterizes isotopy classes of skew configurations with spindle-structure. We use this result in order to define an invariant, spindle-genus, for spindle-configurations. We also slightly simplify the exposition of some known invariants for configurations of skew lines an…
We consider the problem of configuring general-purpose solvers to run efficiently on problem instances drawn from an unknown distribution. The goal of the configurator is to find a configuration that runs fast on average on most instances, and do so with the least amount of total work. It can run a chosen solver on a r…
Optimizes glmnet configuration for better accuracy and efficiency.