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.
Generalizes neural network verification by adding arbitrary cutting planes.
Inspired by recent interests of developing machine learning and data mining algorithms on hypergraphs, we investigate in this paper the semi-supervised learning algorithm of propagating "soft labels" (e.g. probability distributions, class membership scores) over hypergraphs, by means of optimal transportation. Borrowin…
This paper investigates the computational complexity of sparse label propagation which has been proposed recently for processing network structured data. Sparse label propagation amounts to a convex optimization problem and might be considered as an extension of basis pursuit from sparse vectors to network structured d…
The analysis of Belief Propagation and other algorithms for the {\em reconstruction problem} plays a key role in the analysis of community detection in inference on graphs, phylogenetic reconstruction in bioinformatics, and the cavity method in statistical physics. We prove a conjecture of Evans, Kenyon, Peres, and Sch…
Validates composite systems using discrepancy propagation.
Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.
Training Deep Neural Networks that are robust to norm bounded adversarial attacks remains an elusive problem. While exact and inexact verification-based methods are generally too expensive to train large networks, it was demonstrated that bounded input intervals can be inexpensively propagated from a layer to another t…
Paper improves neural network robustness analysis for safety-critical systems.
The belief propagation (BP) algorithm is widely applied to perform approximate inference on arbitrary graphical models, in part due to its excellent empirical properties and performance. However, little is known theoretically about when this algorithm will perform well. Using recent analysis of convergence and stabilit…
Factor graphs are important models for succinctly representing probability distributions in machine learning, coding theory, and statistical physics. Several computational problems, such as computing marginals and partition functions, arise naturally when working with factor graphs. Belief propagation is a widely deplo…
Improves label propagation for weakly supervised learning.
Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of hundreds depending on the underlying network architectures. Meanwhile, interval bound…
Study reveals decurve flows in graph propagation models.
A new approach estimates propagators for trading risky assets.
IBP-R improves verified adversarial robustness with simple, effective interval bound propagation.
We introduce a new class of lower bounds on the log partition function of a Markov random field which makes use of a reversed Jensen's inequality. In particular, our method approximates the intractable distribution using a linear combination of spanning trees with negative weights. This technique is a lower-bound count…
Bandit is a framework for designing sequential experiments. In each experiment, a learner selects an arm and obtains an observation corresponding to . Theoretically, the tight regret lower-bound for the general bandit is polynomial with respect to the number of arms . This makes ba…
Proposes a label propagation framework for domain adaptation.
Loopy and generalized belief propagation are popular algorithms for approximate inference in Markov random fields and Bayesian networks. Fixed points of these algorithms correspond to extrema of the Bethe and Kikuchi free energy. However, belief propagation does not always converge, which explains the need for approach…
Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question whether the adversarially trained networks are truly robust under unknown attacks. In…
Uniform-in-time analysis for Stein Variational Gradient Descent across various metrics.
New algorithm optimizes nonlinear SDEs online with convergence guarantees.
A new stochastic algorithm approximates optimal distributions without requiring propagation of chaos.
Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show promise, they often res…
BPNNs learn to solve combinatorial problems faster and more accurately.
Algorithm maximizes revenue-risk by estimating price impact kernel and optimizing control problems.
Temporal-Difference learning (TD) [Sutton, 1988] with function approximation can converge to solutions that are worse than those obtained by Monte-Carlo regression, even in the simple case of on-policy evaluation. To increase our understanding of the problem, we investigate the issue of approximation errors in areas of…
This paper analyzes how errors accumulate in PCA's deflation method.
Paper proposes faster certified robust training methods with short warmup.
Crowdsourcing systems are popular for solving large-scale labelling tasks with low-paid workers. We study the problem of recovering the true labels from the possibly erroneous crowdsourced labels under the popular Dawid-Skene model. To address this inference problem, several algorithms have recently been proposed, but …
Signals are submanifolds; bounds on energy calculated.
Proposes MCBO for causal Bayesian optimization with model learning and regret bounds.
Unified diffusive bounds for non-linear parabolic equations.
Paper aims to ensure reliable detection of out-of-distribution data with certifiable worst-case guarantees.
Generalized belief propagation converges to optimal solutions on graphs with motifs.
Study probabilistic safety of BNNs under adversarial attacks.
Belief propagation recovers backpropagation results.
Uniform bounds for neural network convergence without strong convexity assumptions.
Gaussian Belief Propagation (BP) algorithm is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly computes marginal density functions from a high dimensional joint density function over a Markov network i…
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…
WAEs offer a statistical understanding of density estimation and error bounds.
A framework uses free probability to analyze Transformer models.
U-Nets use belief propagation for efficient image denoising and classification.
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…
Unified neural network framework for context-aware Gaussian overbounds in uncertainty propagation.
Exact inference in the linear regression model with spike and slab priors is often intractable. Expectation propagation (EP) can be used for approximate inference. However, the regular sequential form of EP (R-EP) may fail to converge in this model when the size of the training set is very small. As an alternative, we …
New method bounds causal effects using local consistency of marginals.
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…