Solves initial value problem for harmonic maps on specific manifolds.
problem Initial value problem for harmonic maps on cohomogeneity one manifolds.
method Setup and solve the initial value problem using equivariant harmonic maps and regular-singular systems.
result Local existence of harmonic maps in a neighborhood of singular orbits.
The dominant energy condition imposes a restriction on initial value pairs found on a spacelike hypersurface of a Lorentzian manifold. In this article, we study the space of initial values that satisfy this condition strictly. To this aim, we introduce an index difference for initial value pairs and compare it to its c…
Solves initial boundary value problem for vacuum Einstein equations and proves geometric uniqueness.
problem Initial boundary value problem for vacuum Einstein equations.
method Formulated IBVP, solved simultaneously in local harmonic coordinates, constructed unique maximal globally hyperbolic solution.
result Vacuum spacetimes satisfying fixed initial-boundary conditions and corner conditions are geometrically unique near the initial surface.
Fenrir uses probabilistic numerics to simplify solving initial value problems.
problem Solving initial value problems in ordinary differential equations.
method Probabilistic numerics and Gauss--Markov regression.
result The method simplifies parameter estimation in ODEs, making it easier and more robust.
Geometrically interpolates rigid body motions with initial and terminal twists.
problem Finding spatial trajectories between prescribed initial and terminal poses.
method Derives solutions for k-IV-TIP and k-BV-TIP for k=1,...,4.
result Automatic cubic interpolation identical to minimum acceleration curve when twists are zero.
This article, written to appear as a chapter in "The Springer Handbook of Spacetime", is a review of the initial value problem for Einstein's gravitational field theory in general relativity. Designed to be accessible to graduate students who have taken a first course in general relativity, the article first discusses …
New boundary conditions improve Hamiltonian analysis in GR.
problem Improving Hamiltonian analysis in GR with IBVP.
method Presented and analyzed new boundary conditions.
result New boundary conditions lead to better Hamiltonian analysis.
Paper enhances RL policies using trust region optimization for offline data.
problem Limited data in offline RL settings.
method Trust region optimization for value enhancement.
result Enhanced policy values with faster convergence.
Proves spacetime positive mass theorem for spin initial data sets with arbitrary ends.
problem Proving the spacetime positive mass theorem for specific spacetime configurations.
method Solving a mixed boundary value problem for the Dirac-Witten operator with a Callias potential.
result Established spacetime positive mass theorem for asymptotically flat spin initial data sets with arbitrary ends.
It is well known that the initialization of weights in deep neural networks can have a dramatic impact on learning speed. For example, ensuring the mean squared singular value of a network's input-output Jacobian is O(1) is essential for avoiding the exponential vanishing or explosion of gradients. The stronger condi…
A new method trains deep networks by separating weight locations from values.
problem Training deep networks efficiently and effectively.
method Lookahead Permutation (LaPerm) to train DNNs by reconnecting weights.
result LaPerm can train DNNs with random and dense, sparse, or single-valued initial weights.
Constructs Lie-Rinehart algebra for Einstein's equations.
problem Initial value problem constraints for Einstein's equations.
method BV-BFV approach to boundary value problems, constructing L∞-algebroid. result Lie-Rinehart algebra comes from slight generalization of Lie algebroid.
This research explores complex-valued neural networks and their implementation.
problem The challenges of implementing complex-valued neural networks and their potential for non-complex data.
method Detailed theory and implementation of CVNN, including Wirtinger calculus, complex backpropagation, and modules like complex layers and activation functions. Python implementation using cvnn toolbox.
result Demonstrates the potential of CVNN for non-complex data through simulations.
In this paper, we firstly give a brief introduction of expectation maximization (EM) algorithm, and then discuss the initial value sensitivity of expectation maximization algorithm. Subsequently, we give a short proof of EM's convergence. Then, we implement experiments with the expectation maximization algorithm (We im…
New method for initializing RBM weights without datasets.
problem No dataset-free weight-initialization for RBMs.
method Statistical mechanical analysis to derive Gaussian distribution with optimized standard deviation.
result Optimal weight initialization improves learning efficiency in RBMs.
This study examines how ChiNext IPOs' initial returns are influenced by regulation regime changes.
problem Investors' behavior and pricing of ChiNext IPOs under different regulation regimes.
method Analysis of three time periods with two different regulation regimes and three sets of listing day trading restrictions.
result Regulation regime changes significantly impact ChiNext IPO pricing and overreaction.
The paper tackles fVaR prediction methods in finance.
problem Predicting future values at risk (fVaR) in finance.
method Various methods including Nested MC-empirical quantile, percentiles from distributions, quantile regressions, and limited inner simulations.
result Improved methods for predicting fVaRs, including those that are computationally efficient.
Unified formula for training dynamics of linear networks combining lazy and balanced regimes.
problem Training dynamics of linear networks in two distinct setups: lazy and balanced/active.
method Unified formula for the evolution of the learned matrix, combining lazy and balanced regimes.
result Unified formula allows for rapid convergence and low rank bias, proving a complete phase diagram.
Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding gradients. In this paper, simplified models of ResNets are analyzed. We argue that good…
Proof of local well-posedness for a specific boundary condition in general relativity.
problem Initial boundary value problem in general relativity with umbilic boundary condition.
method Wave coordinates and key observation of momentum constraint validity for umbilic boundaries.
result Local well-posedness established for the initial boundary value problem.
Study proves convergence of quantized geodesics to Mabuchi geodesics.
problem Convergence of quantized geodesics to Mabuchi geodesics in short time.
method Real-analytic initial data and convergence proof.
result Proves convergence of quantized Bergman geodesics to Mabuchi geodesics.
Proves rigidity for specific initial data sets under the dominant energy condition.
problem Rigidity of initial data sets with boundary and convex polytopes.
method Solution of boundary value problems for Dirac operators and approximations by manifolds with smooth boundary.
result Proves rigidity for compact smooth spin manifolds and convex polytopes under the dominant energy condition.
Under weak regularity assumptions, only, we develop a fully geometric theory of vacuum Einstein spacetimes with T2 symmetry, establish the global well-posedness of the initial value problem for Einstein's field equations, and investigate the global causal structure of the constructed spacetimes. Our weak regularity ass…
GD with large init shows incremental learning in matrix factorization.
problem Understanding GD's behavior with large initial values in matrix factorization.
method Signal-to-noise ratio concepts and inductive arguments.
result Uncovering an incremental learning phenomenon in GD with large initialization.
New method for initializing low-rank neural networks improves performance.
problem Training low-rank neural networks efficiently and accurately.
method Inspired by function approximation, proposes a novel low-rank initialization framework.
result Demonstrates significant gap between spectral and low-rank initialization approaches.
Like many numerical methods, solvers for initial value problems (IVPs) on ordinary differential equations estimate an analytically intractable quantity, using the results of tractable computations as inputs. This structure is closely connected to the notion of inference on latent variables in statistics. We describe a …
Neural IVP solves IVPs with neural networks, overcoming scaling and conditioning issues.
problem Solving initial value PDEs with neural networks is challenging due to numerical errors and limited scalability.
method Developed an ODE-based approach to solve IVPs with neural networks, preventing ill-conditioning and scaling issues.
result Neural IVP solves challenging PDEs with neural networks efficiently and accurately.
We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function, q-value function, or the optimal policy the algorithm can determine which rewards w…
Study geometric equations on cohomogeneity one manifolds near singular orbits.
problem Solving geometric equations like Ricci, Einstein, and soliton near singular orbits.
method Special assumption simplifies proof; general case solved in Part II.
result Existence and uniqueness of solutions near singular orbits.
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.
We find necessary and sufficient conditions ensuring that the vacuum development of an initial data set of the Einstein's field equations admits a conformal Killing vector. We refer to these conditions as conformal Killing initial data (CKID) and they extend the well-known Killing initial data (KID) that have been know…
We study the problem of inviscid slightly compressible fluids in a bounded domain. We find a unique solution to the initial-boundary value problem and show that it is near the analogous solution for an incompressible fluid provided the initial conditions for the two problems are close. In particular, the divergence of …
New sample complexity bounds for linear predictors and neural networks, focusing on initialization.
problem Understanding sample complexity for vector-valued linear predictors and neural networks, especially under initialization-dependent conditions.
method Size-independent bounds on Frobenius norm distance from a fixed reference matrix, applying to vector-valued predictors and neural networks.
result Established new sample complexity bounds for feed-forward neural networks, resolving open questions and introducing a new learnable problem.
The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet despite significant empirical and theoretical analysis, relatively little has been p…
Improves LSTM performance by initializing states via manifold learning.
problem Improving LSTM performance through better initialization.
method Learning an intrinsic data manifold to initialize LSTM internal states.
result Improved LSTM performance through consistent initialization.
New insights show stochastic initialization prevents token clustering in deep Transformers.
problem Understanding token dynamics in deep stochastic Transformers.
method Analysis of deep Transformers with random initialization noise, proving convergence to an interacting-particle system on the sphere.
result Initialization noise prevents token clustering, leading to antipodal formations.
Set-valued risk measures on Ldp with 0≤p≤∞ for conical market models are defined, primal and dual representation results are given. The collection of initial endowments which allow to super-hedge a multivariate claim are shown to form the values of a set-valued sublinear (coherent) risk measure. Sc…
Singular Value Decomposition (SVD) constitutes a bridge between the linear algebra concepts and multi-layer neural networks---it is their linear analogy. Besides of this insight, it can be used as a good initial guess for the network parameters, leading to substantially better optimization results.
Adaptive optimal control using value iteration initiated from a stabilizing control policy is theoretically analyzed in terms of stability of the system during the learning stage without ignoring the effects of approximation errors. This analysis includes the system operated using any single/constant resulting control …
The paper examines the neural tangent kernel for PINNs solving general PDEs and finds convergence conditions.
problem Analyzing the convergence of neural tangent kernel for PINNs solving general PDEs.
method Analysis of NTK initialization and convergence during training for general PDEs using PINNs.
result Homogeneity of differential operators is crucial for NTK convergence.
Proposes a method to optimize neural network initialization using marginal likelihood maximization.
problem Optimizing hyperparameters for neural network initialization.
method Leverages the connection between neural networks and Gaussian processes to infer optimal hyperparameters.
result Marginal likelihood maximization provides near-optimal prediction performance on MNIST classification tasks.
New initialization schemes preserve fractional moments of weights in deep networks, improving training and test performance.
problem Heavy-tailed distribution of stochastic gradients in DNNs during training.
method Developed initialization schemes that preserve any given fractional moment of order s < 2 over layers for various activations.
result The network output admits a heavy-tailed distribution with finite moments, improving training and test performance.
Global implicit function theorem for Fréchet spaces, solving derivative loss problems.
problem Solving initial value problems with derivative loss in Fréchet spaces.
method Global implicit function theorems for Keller's Cc1-mappings in Fréchet spaces, applied through submersions and transversality. result Global existence and uniqueness of solutions to initial value problems with derivative loss.
Residual networks (ResNet) and weight normalization play an important role in various deep learning applications. However, parameter initialization strategies have not been studied previously for weight normalized networks and, in practice, initialization methods designed for un-normalized networks are used as a proxy.…
In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encod…
Recent pruning methods at initialization fall short of random pruning's accuracy.
problem Improving neural network accuracy through pruning at initialization.
method Various pruning methods (SNIP, GraSP, SynFlow, magnitude pruning) are evaluated; per-layer pruning decisions are proposed.
result Randomly shuffling or sampling initial weights preserves or improves accuracy, suggesting challenges with pruning heuristics.
We prove local existence for the second order Renormalization Group flow initial value problem on closed Riemannian manifolds (M,g) in general dimensions, for initial metrics whose sectional curvatures KP satisfy the condition 1+αKP>0, at all points p∈M and planes P⊂TpM. This extends results…
The paper constructs Ricci flow solutions for non-smooth metrics in four dimensions.
problem Constructing Ricci flow solutions for non-smooth metrics in four dimensions.
method Ricci DeTurck flow on closed manifolds with initial values in W2,2. result Constructs solutions to Ricci flow for non-smooth metrics in four dimensions.