Neural surrogate predicts SPN rates from token trajectories.
problem Challenging parameter estimation in SPNs with covariates.
method 1D Convolutional Residual Network trained on Gillespie-simulated SPN realizations.
result Surrogate predicts rate-function coefficients with RMSE = 0.043.
In complex processes, various events can happen in different sequences. The prediction of the next event given an a-priori process state is of importance in such processes. Recent methods have proposed deep learning techniques such as recurrent neural networks, developed on raw event logs, to predict the next event fro…
Synthetic Petri Dish predicts neural architecture performance faster.
problem Expensive NAS evaluation process with ground-truth data.
method Instantiates motifs in small networks, evaluates with few synthetic samples.
result Significantly higher accuracy in predicting motif performance.
The paper studies almost complex torus manifolds using graphs and Hirzebruch genera, proving properties of their fixed points and cohomology.
problem Understanding the fixed points and cohomology of almost complex torus manifolds.
method Using directed labeled multigraphs and Hirzebruch genera to encode and analyze the manifolds.
result Almost complex torus manifolds have positive Todd genus and at least n+1 fixed points.
SDE-Net quantifies uncertainty in deep nets using stochastic dynamics.
problem Uncertainty quantification in deep neural networks.
method Viewing DNN transformations as state evolution of a stochastic dynamical system, introducing a Brownian motion term for epistemic uncertainty.
result SDE-Net outperforms existing methods in uncertainty estimation across various tasks.
fSDE-Net generates time series with long-term memory using neural networks.
problem Generating time series with long-term memory from irregularly sampled data.
method fSDE-Net: neural fractional Stochastic Differential Equation Network using fractional Brownian motion.
result fSDE-Net can replicate distributional properties of real time-series data.
Learning to Optimize is a recently proposed framework for learning optimization algorithms using reinforcement learning. In this paper, we explore learning an optimization algorithm for training shallow neural nets. Such high-dimensional stochastic optimization problems present interesting challenges for existing reinf…
Bayesian Neural Nets improve model stability and fit.
problem Improving model stability and fit in time series prediction.
method Assign Bayesian Neural Nets to drift and diffusion terms of SDE, infer posterior using SGLD.
result Significantly improved stability and better model fit on benchmarks.
Delay-SDE-net models time series with memory and uncertainty, outperforming other models.
problem Accurately modeling time series with memory and uncertainty.
method Stochastic delay differential equations (SDDEs) neural network model with aleatoric and epistemic uncertainty.
result The Delay-SDE-net consistently outperforms other models in predicting time series values and uncertainties.
Improves model accuracy for neural nets in stochastic dynamics with partial prior knowledge.
problem Stability and accuracy in neural nets modeling stochastic dynamics with many parameters.
method Three steps: probabilistic weights, partial knowledge incorporation, and PAC-Bayesian training.
result Improved model fit with partial and noisy prior knowledge.
Proposes a new deep learning model for uncertainty quantification and propagation.
problem High-dimensional uncertainty quantification and propagation problems.
method Integrates U-net with Gaussian Gated Linear Network (GGLN) to create GLU-net.
result Less complex architecture with 44% fewer parameters than existing models.
While stochastic gradient descent (SGD) and variants have been surprisingly successful for training deep nets, several aspects of the optimization dynamics and generalization are still not well understood. In this paper, we present new empirical observations and theoretical results on both the optimization dynamics and…
Derives fluctuation theorems and thermodynamic uncertainty relations for systems modeled as Bayes nets.
problem Entropy production in interacting systems modeled as Bayes nets.
method Derives fluctuation theorems and thermodynamic uncertainty relations for arbitrary sets and conditioned sets of systems in Bayes nets.
result Relates the entropy production of the overall system to the precisions of probability currents in individual systems.
Paper assesses GMMB in VAs using FST for accurate net liability calculations.
problem Risk management of GMMB under stochastic mortality and regime-switching.
method Net liability model with FST algorithm for accurate numeric solutions.
result FST algorithm provides reliable results for net liability of GMMB.
Proposes a new method to learn operators for stochastic problems using DeepONet with autoencoder.
problem Efficiently solve forward and inverse stochastic problems with limited data.
method MultiAuto-DeepONet, a multi-resolution autoencoder DeepONet model.
result The model effectively handles high-dimensional stochastic inputs and reduces the number of trainable parameters.
Let M be a manifold homotopy equivalent to the complex projective space $\C P^m$. Petrie conjectured that M has standard total Pontrjagin class if M admits a non-trivial action by S1. We prove the conjecture for m<12 under the assumption that the action extends to a nice Pin(2)-action with fixed point. The…
Study on length spectrum of random hyperbolic 3-manifolds.
problem Understanding the length spectrum of random hyperbolic 3-manifolds.
method Modeling random hyperbolic 3-manifolds using truncated tetrahedra and analyzing their length spectrum as volume tends to infinity.
result The length spectrum converges in distribution to a Poisson point process with a computable intensity λ as volume increases.
The paper clarifies the approximation of SGD with Ito SDEs for finite learning rates.
problem Theoretical justification and experimental verification of the Ito SDE approximation for finite learning rates in SGD.
method An efficient simulation algorithm SVAG and a necessary condition test for the SDE approximation.
result The Ito SDE approximation can meaningfully capture training and generalization properties of deep nets with finite learning rates.
Directly proves logarithmic systolic growth for all hyperbolic surfaces.
problem Proving logarithmic systolic growth for all hyperbolic surfaces.
method Using original Brooks/Buser-Sarnak surfaces through a direct approach.
result Directly proves logarithmic systolic growth for all hyperbolic surfaces.
Study shows systole behavior changes significantly for large genus hyperbolic surfaces.
problem Understanding systole behavior in large genus hyperbolic surfaces.
method Analysis of random surfaces with respect to Weil-Petersson volume.
result Expected value of separating systole behaves like 2logg for large genus. For G an almost-connected Lie group, we study G-equivariant index theory for proper co-compact actions with various applications, including obstructions to and existence of G-invariant Riemannian metrics of positive scalar curvature. We prove a rigidity result for almost-complex manifolds, generalising Hattori's result…
APAC-Net solves high-dimensional stochastic MFGs using neural networks.
problem High-dimensional stochastic mean-field games.
method Alternating population and control neural networks, parameterizing value and density functions.
result Solves up to 100-dimensional MFG problems.
Classifies circle actions on 6D manifolds with 4 fixed points.
problem Classifying circle actions on 6D manifolds with specific fixed points.
method Analyzes fixed point data and proves agreement with known actions.
result Agrees with actions on 6-spheres or CP3. The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems. Or have we simply not tried hard enough for kernel methods? Here we propose an approach that scales up kernel methods using a novel concept called "doubly stochastic functional grad…
Study on systole of random hyperbolic 3-manifolds, proving limit exists and calculating it.
problem Understanding the systole of random hyperbolic 3-manifolds.
method Modeling random hyperbolic 3-manifolds using truncated tetrahedra, calculating expected systole limit as volume increases.
result Closed formula and numerical approximation for the limit of the expected systole as volume tends to infinity.
Model assesses loan profitability under changing credit conditions.
problem Financial institutions face risks of default and prepayment.
method Develops a Random Net Present Value (RNPV) model to evaluate profitability.
result Mean and variance of RNPV calculated at individual and portfolio levels.
Let X be a smooth manifold belonging to one of these three collections: acyclic manifolds (compact or not, possibly with boundary), compact connected manifolds (possibly with boundary) with nonzero Euler characteristic, integral homology spheres. We prove that Diff(X) is Jordan. This means that there exists a const…
Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to th…
Optimizes gradual reduction of excess carbon emissions to net-zero.
problem Achieving net-zero carbon emissions through gradual reduction of excess emissions.
method Stochastic control approach to identify optimal emission strategy under constraints.
result Identifies the emission strategy that maximizes future profit from excess emissions.
In deep latent Gaussian models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlinear map, such as a feedforward neural net, and add a small independent Gaussian perturbation. This work considers the diffusion limit of suc…
Estimates matrix trace optimization with statistical learning theory.
problem Optimizing trace of parameter-dependent matrices.
method Monte Carlo estimator with bounds derived from epsilon nets and generic chaining.
result Predicts small sampling amount for matrices with small off-diagonal mass.
Modeling climate change costs with stochastic interest rates shows inequality, but funding abatement can reduce this.
problem Evaluating the costs and benefits of climate change mitigation with uncertain discount rates.
method Amended DICE model with stochastic interest rates and funding abatement costs.
result Introducing funding abatement can reduce intergenerational inequality in climate change costs.
In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADMM pair}), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of …
CDPL-Net integrates CNN and DL for better image representation.
problem Improving image representation learning by combining CNN and DL.
method CDPL-Net architecture combining CNN and DPL layers, using l1-norm for sparse representation, and efficient stochastic gradient descent.
result Enhanced performance compared to state-of-the-art methods.
BCD Nets use variational inference to estimate DAGs with uncertainty.
problem Uncertainty in inferring causal graphs from limited data.
method Variational inference framework for Bayesian DAG estimation.
result BCD Nets outperform maximum-likelihood methods in low data regimes.
Algorithm of multicurrency trading at the market of Forex is realized on the basis of nonlinear stochastic wavelets. The distinctive feature of the algorithm is the possibility of weakly- and strongly connected horizontal self-assemblies, as well as use of nested structures. On-line trading with eight currency couples …
Study on geodesics and eigenvalues on random hyperbolic surfaces with cusps.
problem Counting short geodesics and small eigenvalues on random hyperbolic surfaces.
method Rescaling and convergence to a Poisson point process.
result The probability of having at least k=o(n) arbitrarily small eigenvalues tends to 1 as no∞. NANSDE-Net models time series with memory using neural ARMA-type noise.
problem Modeling time series with long- or short-memory characteristics.
method Developed NANSDE-Net, a generative model that incorporates Neural Network-kernel ARMA-type noise.
result NANSDE-Net matches or outperforms existing models in reproducing long- and short-memory features of data.
Automatic debiasing for causal and policy effects using Neural Nets and Random Forests.
problem Estimating causal and policy effects from high-dimensional or non-parametric regression functions.
method Automatic learning of Riesz representation using Neural Nets and Random Forests.
result Automatic debiasing method performs well compared to state-of-the-art algorithms.
We develop a scalable method for Bayesian neural networks with stochastic differential equations.
problem Uncertainty quantification in deep neural networks.
method Gradient-based stochastic variational inference in continuous-depth Bayesian neural networks.
result Gradient estimator with zero variance as the approximation improves.
Mack-Net model combines Mack's model with RNNs for better insurance liability estimation.
problem Accurate estimation of insurance liabilities for better financial decision-making.
method Integrates Mack's reserving model with Recurrent Neural Networks (RNNs).
result Improves accuracy of general insurance liability assessment.
We study a sparse negative binomial regression (NBR) for count data by showing the non-asymptotic advantages of using the elastic-net estimator. Two types of oracle inequalities are derived for the NBR's elastic-net estimates by using the Compatibility Factor Condition and the Stabil Condition. The second type of oracl…
Hierarchical Bayesian networks and neural networks with stochastic hidden units are commonly perceived as two separate types of models. We show that either of these types of models can often be transformed into an instance of the other, by switching between centered and differentiable non-centered parameterizations of …
This is a survey of our research on geometric structures of projective embeddings and includes some topics of our talks in several symposia during 1990-99. We clarify our main problem, which is to construct a kind of geometric composition series of projective embeddings. The concept of "geometric composition series" is…
LGS-Net improves NCO performance on combinatorial optimization tasks.
problem NP-hard combinatorial optimization problems in logistics, manufacturing, and drug discovery.
method LGS-Net uses a latent space model that conditions on problem instances and introduces Latent Guided Sampling for efficient inference.
result Empirical results show state-of-the-art performance on benchmark routing tasks.
Study on random hyperbolic surfaces with many cusps, focusing on tight geodesics.
problem Understanding length statistics of geodesics on random hyperbolic surfaces with cusps.
method Recursion formula for tight Weil-Petersson volumes and generalization of Mirzakhani's integration formula.
result Recovery of Poisson point process in large genus limit for length statistics of tight geodesics.
The paper explores discrete isothermic nets using checkerboard patterns in quadrilateral nets.
problem Defining and understanding discrete isothermic nets in quadrilateral nets.
method Using checkerboard patterns and discrete differential geometry to define and analyze isothermic nets.
result The class of isothermic nets is invariant under dualization and Moebius transformations.
We investigate the common underlying discrete structures for various smooth and discrete nets. The main idea is to impose the characteristic properties of the nets not only on elementary quadrilaterals but also on larger parameter rectangles. For discrete planar quadrilateral nets, circular nets, Q∗-nets and conical…