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.
Improved BP algorithm outperforms loopy BP in MAP inference.
One pixel can significantly alter deep neural network outputs, revealing propagation patterns and vulnerability hotspots.
Improved diffusion map enhances manifold regularization for semi-supervised learning.
Synaptic strength can be seen as probability to propagate impulse, and according to synaptic plasticity, function could exist from propagation activity to synaptic strength. If the function satisfies constraints such as continuity and monotonicity, neural network under external stimulus will always go to fixed point, a…
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating bac…
An analytico-geometric reflection principle is established by means of normal deformations of analytic discs.
We improve neural network explainability by bypassing batch normalization.
Functoriality proved for higher rho invariants of elliptic operators.
Approximations of loopy belief propagation, including expectation propagation and approximate message passing, have attracted considerable attention for probabilistic inference problems. This paper proposes and analyzes a generalization of Opper and Winther's expectation consistent (EC) approximate inference method. Th…
Proposes a semi-implicit back propagation method for neural networks.
Visualizes ConvNets without confounding effects.
DistGP models multi-robot mapping with distributed Gaussian process learning.
Finding the most probable assignment (MAP) in a general graphical model is known to be NP hard but good approximations have been attained with max-product belief propagation (BP) and its variants. In particular, it is known that using BP on a single-cycle graph or tree reweighted BP on an arbitrary graph will give the …
New algorithm constrains SOMs to create supervised low-dimensional mappings.
We introduce a mixed-effects model to learn spatiotempo-ral patterns on a network by considering longitudinal measures distributed on a fixed graph. The data come from repeated observations of subjects at different time points which take the form of measurement maps distributed on a graph such as an image or a mesh. Th…
Study eigenvalues and eigenvectors in neural networks, focusing on signal propagation.
We propose to learn a kernel-based message operator which takes as input all expectation propagation (EP) incoming messages to a factor node and produces an outgoing message. In ordinary EP, computing an outgoing message involves estimating a multivariate integral which may not have an analytic expression. Learning suc…
New method for finding function correspondences in binary programs.
Study probabilistic safety of BNNs under adversarial attacks.
We prove the equivalence of several natural notions of conformal maps between sub-Riemannian manifolds. Our main contribution is in the setting of those manifolds that support a suitable regularity theory for subelliptic -Laplacian operators. For such manifolds we prove a Liouville-type theorem, i.e., 1-quasiconform…
Many practical machine learning tasks employ very deep convolutional neural networks. Such large depths pose formidable computational challenges in training and operating the network. It is therefore important to understand how fast the energy contained in the propagated signals (a.k.a. feature maps) decays across laye…
MAP inference for general energy functions remains a challenging problem. While most efforts are channeled towards improving the linear programming (LP) based relaxation, this work is motivated by the quadratic programming (QP) relaxation. We propose a novel MAP relaxation that penalizes the Kullback-Leibler divergence…
In Lorentzian manifolds of any dimension the concept of causal tensors is introduced. Causal tensors have positivity properties analogous to the so-called ``dominant energy condition''. Further, it is shown how to build, from ANY given tensor , a new tensor quadratic in and ``positive'', in the sense that it is …
New weight initialisation for ICNNs accelerates learning and improves generalization.
PRCD-MAP learns to trust imperfect priors in causal discovery, improving accuracy and robustness.
Generalized belief propagation converges to optimal solutions on graphs with motifs.
Distribution regression has recently attracted much interest as a generic solution to the problem of supervised learning where labels are available at the group level, rather than at the individual level. Current approaches, however, do not propagate the uncertainty in observations due to sampling variability in the gr…
Belief propagation recovers backpropagation results.
This study maps systemic risks in TradFi and DeFi, highlighting their interdependence.
A susceptibility propagation that is constructed by combining a belief propagation and a linear response method is used for approximate computation for Markov random fields. Herein, we formulate a new, improved susceptibility propagation by using the concept of a diagonal matching method that is based on mean-field app…
SparseTrain uses dynamic sparsity in training deep neural networks on CPUs.
Paper proposes a new ML approach using only additions and thresholding.
Power spectral density (PSD) maps providing the distribution of RF power across space and frequency are constructed using power measurements collected by a network of low-cost sensors. By introducing linear compression and quantization to a small number of bits, sensor measurements can be communicated to the fusion cen…
Variational inference is a powerful concept that underlies many iterative approximation algorithms; expectation propagation, mean-field methods and belief propagations were all central themes at the school that can be perceived from this unifying framework. The lectures of Manfred Opper introduce the archetypal example…
Propagating input uncertainty through non-linear Gaussian process (GP) mappings is intractable. This hinders the task of training GPs using uncertain and partially observed inputs. In this paper we refer to this task as "semi-described learning". We then introduce a GP framework that solves both, the semi-described and…
RadioUNet uses deep learning to estimate pathloss in urban environments.
Ensemble clustering has been a popular research topic in data mining and machine learning. Despite its significant progress in recent years, there are still two challenging issues in the current ensemble clustering research. First, most of the existing algorithms tend to investigate the ensemble information at the obje…
Study reveals decurve flows in graph propagation models.
Unified model combines feature and label propagation for semi-supervised classification.
Improved error correction using neural networks and belief propagation.
Random feature maps improve forecasting with cheaper computation.
A new approach estimates propagators for trading risky assets.
This thesis investigates belief propagation's performance in graphical models with loops.
Maximum A posteriori Probability (MAP) inference in graphical models amounts to solving a graph-structured combinatorial optimization problem. Popular inference algorithms such as belief propagation (BP) and generalized belief propagation (GBP) are intimately related to linear programming (LP) relaxation within the She…
LNPE enhances local connections in embeddings using extended neighbor propagation.
Decoupled GCN is shown to be equivalent to label propagation.
The back-propagation algorithm is the cornerstone of deep learning. Despite its importance, few variations of the algorithm have been attempted. This work presents an approach to discover new variations of the back-propagation equation. We use a domain specific lan- guage to describe update equations as a list of primi…
A new method for target propagation using iterative approximations converges fast and is more biologically plausible.