A decentralized MARL algorithm for value propagation in non-linear settings.
problem Decentralized coordination in multi-agent systems with different local rewards.
method Decentralized optimization and value propagation algorithm.
result Non-asymptotic convergence rate of 1/T in nonlinear function approximation.
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Proposes dynamic channel pruning during neural network training.
problem Pruning neural networks during training to reduce computational cost and improve efficiency.
method Dynamic channel propagation to update channel utility values and selectively prune channels.
result Our scheme trains and prunes neural networks simultaneously, achieving superior performance.
A new framework explains mixed models by propagating Shapley values.
problem Making complex models like neural networks and stacked models explainable for healthcare applications.
method DeepSHAP framework for layer-wise propagation of Shapley values.
result DeepSHAP enables attributions for mixed models and theoretically justifies attributions with respect to a background distribution.
Geometric wave propagator defined on Riemannian manifolds.
problem Wave equation on Riemannian manifolds.
method Geometric approach to constructing propagator as oscillatory integral.
result Explicit small time asymptotic expansion of subprincipal symbol.
One pixel can significantly alter deep neural network outputs, revealing propagation patterns and vulnerability hotspots.
problem Understanding how a single pixel modification affects deep neural networks.
method Propagation Maps and locality analysis to visualize and understand the impact of pixel modifications.
result One pixel modifications can propagate through deep networks, affecting the final output and revealing vulnerability patterns.
The paper analyzes error propagation in dynamic programming for stochastic control and option pricing.
problem Error propagation in dynamic programming for stochastic control and option pricing.
method Formulated a general dynamic programming framework, used RKHSs for nonparametric regression, and Monte Carlo subsampling for estimating continuation value.
result Proposed a rigorous error decomposition and control mechanism for error propagation in dynamic programming.
Optimal portfolio choice with cross-impact propagators, solving complex equations.
problem Maximizing revenue-risk in a continuous-time portfolio choice problem with cross-impact.
method Formulated as a maximization problem, solved explicitly using operator resolvents and stochastic Fredholm equations.
result Sufficient conditions for the absence of price manipulation, providing financial insights.
We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation. In contrast to the conventional use of the experience replay with uniform random sampling, our agent samples a whole episode and successively propagates the value of a state to its previous states.…
Geometric approach to Dirac operator evolution on spacetimes.
problem Constructing the Cauchy evolution operator for Lorentzian Dirac operators.
method Realizing the operator as a sum of oscillatory integrals, relating to Feynman propagator.
result Relating Cauchy evolution operators to Feynman propagators and constructing Hadamard states.
Field theory explains optimal scaling in ResNets for signal propagation.
problem Understanding optimal scaling parameter for ResNet performance.
method Finite-size field theory for ResNets to study signal propagation and scaling.
result Analytical expressions for optimal scaling parameter, independent of other hyperparameters.
Global propagator for massless Dirac operator defined and analyzed.
problem Analyzing the massless Dirac operator on 3-manifolds.
method Constructing propagator as sum of oscillatory integrals, providing global definitions and small time expansions.
result Explicit calculation of propagators' symbols and coefficients in eigenvalue counting functions.
Optimal liquidation strategy with price impact and signal exploitation.
problem Maximizing revenue-risk in a market with transient and temporary price impact.
method Infinite dimensional stochastic control approach, backward stochastic differential equation, operator-valued Riccati equation.
result Explicit expression for the optimal trading strategy.
Polynomial-time method approximates Shapley values for deep neural networks.
problem Lack of reliable attribution methods for deep neural networks.
method Polynomial-time approximation of Shapley values using uncertainty propagation.
result Our method produces significantly better approximations of Shapley values than existing methods.
Proves well-posedness for Einstein equations with totally geodesic timelike boundary condition.
problem Initial boundary value problem for Einstein equations with specific geometric boundary condition.
method ADM system, parallelly propagated orthonormal frame, modified evolution equations, hyperbolic systems, constraints propagation.
result First well-posedness result for Einstein equations with totally geodesic timelike boundary condition.
Quantum propagation studied for Berezin-Toeplitz operators.
problem Asymptotic behavior of quantum propagators and spectral projectors.
method Geometric analysis of Hamiltonian flows and Maslov indices.
result Introduction of quantum states associated with Lagrangian submanifolds.
A number of problems in statistical physics and computer science can be expressed as the computation of marginal probabilities over a Markov random field. Belief propagation, an iterative message-passing algorithm, computes exactly such marginals when the underlying graph is a tree. But it has gained its popularity as …
Proposes a new neural network architecture inspired by biology to improve learning and information flow.
problem Improving artificial neural networks to match biological neuron properties like multidirectional propagation and probabilistic modeling.
method Extends KAN approach with joint distribution neurons that can propagate values and distributions, including variance and higher-order moments.
result Proposed architecture can predict and propagate distributions, including expected values and variances.
Formula for complex SVD backpropagation developed.
problem No specific problem stated; focuses on complex SVD.
method Back propagation formula for complex SVD developed.
result Back propagation formula for complex SVD created.
Uniform-in-time analysis for Stein Variational Gradient Descent across various metrics.
problem Understanding long-term behavior of finite-particle systems in relation to their mean-field limits.
method Developed uniform-in-time propagation-of-chaos results for continuous-time SVGD using cutoff strategies and finite-dimensional theories.
result Uniform-in-time propagation-of-chaos bounds in various metrics, including Langevin kernel Stein discrepancy, Wasserstein-1, and Wasserstein-2 distances.
The paper analyzes the value discrepancies of imitation learning methods.
problem Analyzing the value discrepancies of imitation learning methods.
method Discrepancy propagation analysis for infinite-horizon settings.
result GAIL has less compounding errors than behavioral cloning.
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…
Modeling financial contagion through bank networks, revealing solvency correlations.
problem Understanding how financial shocks propagate through interconnected banks.
method Simulated financial network of 100 banks, randomly generated with varying link probabilities, and shocks applied to 15 banks.
result Ranges of probability values and banks' solvency are positively correlated.
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…
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…
A new method improves label propagation for unsupervised domain adaptation.
problem Improving unsupervised domain adaptation through semi-supervised learning techniques.
method Label Propagation with Augmented Anchors (A2LP) for UDA. result A2LP improves over representative UDA methods and benchmarks. Wave propagator constructed on globally hyperbolic spacetimes.
problem Wave propagation on globally hyperbolic spacetimes.
method Reinterpretation of wave propagator construction on ultrastatic Lorentzian manifolds, reduction to static backgrounds, generalization to globally hyperbolic spacetimes.
result Global wave propagator constructed on globally hyperbolic spacetimes.
Deep networks trained with Hebbian updates perform similarly to back-propagation on image datasets.
problem Training deep networks with realistic asymmetric connections and updates.
method Use Hebbian updates with separate feedforward and feedback weights, and local rule for updates.
result Similar performance to back-propagation achieved with Hebbian updates on challenging image datasets.
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…
New method combines Bloom filters and belief propagation for efficient group testing.
problem Optimizing group testing for COVID-19 samples under practical constraints.
method Combining Bloom filters with belief propagation for scalability and accuracy.
result Strong empirical performance without mixing more than a chosen number of patients.
Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Her…
Algorithm maximizes revenue-risk by estimating price impact kernel and optimizing control problems.
problem Maximizing revenue-risk in a risky asset liquidation with unknown price impact.
method Alternates exploration and exploitation phases, uses novel kernel estimation and stability results.
result Sublinear regret achieved with high probability.
Framework improves PV forecasting by accounting for missing data uncertainty.
problem Uncertainty from missing data in PV power data.
method Combines stochastic multiple imputation with Rubin's rule.
result Improves prediction interval calibration without sacrificing point prediction accuracy.
We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the mode…
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…
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics for layerwise input normalization during training which makes the estimates of …
We consider probabilistic multinomial probit classification using Gaussian process (GP) priors. The challenges with the multiclass GP classification are the integration over the non-Gaussian posterior distribution, and the increase of the number of unknown latent variables as the number of target classes grows. Expecta…
Generalized belief propagation converges to optimal solutions on graphs with motifs.
problem Understanding belief propagation on loopy graphs.
method Study of generalized belief propagation on graphs with motifs.
result Generalized belief propagation converges to the global optimum of the Bethe free energy.
We investigate the initial value problem for the Einstein-Euler equations of general relativity under the assumption of Gowdy symmetry on T3, and we construct matter spacetimes with low regularity. These spacetimes admit, both, impulsive gravitational waves in the metric (for instance, Dirac mass curvature singularitie…
Belief propagation recovers backpropagation results.
problem Connection between backpropagation and belief propagation poorly understood.
method Converted backpropagation input to belief propagation input and showed results.
result Backpropagation is a special case of belief propagation.
We consider the problem of reinforcement learning over episodes of a finite-horizon deterministic system and as a solution propose optimistic constraint propagation (OCP), an algorithm designed to synthesize efficient exploration and value function generalization. We establish that when the true value function lies wit…
Machine learning models predict earthquake rupture dynamics efficiently.
problem Challenges in simulating earthquake rupture dynamics due to uncertainties in physics.
method Developed two machine learning models (ANN and RF) to predict rupture propagation using a database of 1600 simulations.
result Both RF and ANN models predict rupture propagation with over 81% accuracy and can infer important factors for rupture.
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…
INNs produce interval-valued uncertainty scores for DNNs.
problem Uncertainty quantification in deep neural networks.
method Data-driven interval propagating network using interval arithmetic.
result INNs produce sensible lower and upper bounds for prediction error.
Proves existence and uniqueness of calibrated LSV model.
problem Calibrating a local stochastic volatility model to market data.
method Proves strong existence and uniqueness of solution to a McKean-Vlasov SDE.
result Establishes well-posedness of a calibrated two-factor LSV model.
XAI identifies key time steps for early crop classification.
problem Early crop classification with high accuracy and timeliness.
method Training a baseline model with LRP to identify important time steps.
result Identified a 21st April 2019 to 9th August 2019 timeframe with 0.75% accuracy loss.
Noise stability improves understanding of Transformer models.
problem Lack of robustness metrics for real-valued domains and junta-like input dependence in modern LLMs.
method Proposed noise stability as a new metric and developed a practical regularization method.
result Noise stability regularization method accelerates training by 35-75%.
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…