We study the mean escape time in a market model with stochastic volatility. The process followed by the volatility is the Cox Ingersoll and Ross process which is widely used to model stock price fluctuations. The market model can be considered as a generalization of the Heston model, where the geometric Brownian motion…
We solve the escape problem for the Heston random diffusion model. We obtain exact expressions for the survival probability (which ammounts to solving the complete escape problem) as well as for the mean exit time. We also average the volatility in order to work out the problem for the return alone regardless volatilit…
New PINNs method improves accuracy in computing Mean Escape Time from bounded domains.
problem Computing Mean Escape Time from bounded domains with high accuracy.
method Boundary-adapted Physics-Informed Neural Networks (PINNs) with exact Dirichlet boundary enforcement.
result Derivation of H2(Ω) a priori error bounds for PINNs with normalized distance approximations. SGD's escape rate depends on log loss barrier, not linear loss barrier.
problem Understanding the escape rate of SGD from local minima.
method Derived a stochastic differential equation (SDE) with additive noise from SGD's multiplicative noise property.
result The log loss barrier determines the escape rate of SGD, not the linear loss barrier.
Classifies conformal transformations in spacetimes without observer horizons.
problem Understanding conformal transformations in spacetimes without observer horizons.
method Proves classification of conformal transformations into two types: escaping and non-escaping.
result Conformal transformations of Einstein's static universe are classified.
We shortly review the statistical properties of the escape times, or hitting times, for stock price returns by using different models which describe the stock market evolution. We compare the probability function (PF) of these escape times with that obtained from real market data. Afterwards we analyze in detail the ef…
The usual development of the continuous-time random walk (CTRW) proceeds by assuming that the present is one of the jumping times. Under this restrictive assumption integral equations for the propagator and mean escape times have been derived. We generalize these results to the case when the present is an arbitrary tim…
New method controls mean exit time in stochastic systems using machine learning and quasipotential.
problem Controlling mean exit time in stochastic dynamical systems with white noise.
method Developed a neural network to compute the quasipotential function and designed an algorithm to calculate the controller.
result Effective and accurate control strategy demonstrated through numerical experiments.
Gradient descent can take exponentially long to escape saddle points in 2D.
problem Worst-case inefficiency of gradient descent in non-convex optimization.
method Analysis of gradient descent's performance on 2D functions.
result Gradient descent can take exponentially long to escape saddle points.
Houdini finds high-dimensional saddle points under few constraints.
problem Escaping from saddle points in high-dimensional spaces with constraints.
method Gradient descent methods under logarithmic inequality constraints.
result Polynomial time algorithms for escaping saddle points under constraints.
Paper learns Koopman operator from sparse data, escaping function space constraints.
problem Learning Koopman operator from non-closed function spaces.
method Operator stochastic approximation algorithm using conditional mean embeddings (CME).
result Online sparse learning algorithm with trajectory-based sampling guarantees.
Although gradient descent (GD) almost always escapes saddle points asymptotically [Lee et al., 2016], this paper shows that even with fairly natural random initialization schemes and non-pathological functions, GD can be significantly slowed down by saddle points, taking exponential time to escape. On the other hand, g…
HA-SME models SGD dynamics with Hessian info for better escaping behaviors.
problem Capturing the escaping behaviors of SGD from stationary points.
method HA-SME, a novel SDE with Hessian info in drift and diffusion.
result HA-SME achieves best approximation error and recovers SGD dynamics for quadratics.
Study shows how anisotropic data affects learning dynamics in phase retrieval.
problem Understanding learning dynamics in phase retrieval with anisotropic Gaussian inputs.
method Developed a tractable reduction to reveal a three-phase trajectory and derived scaling laws.
result Found that anisotropy leads to a three-phase trajectory: fast escape, slow convergence, and spectral-tail learning.
New metrics help predict Brownian motion on surfaces and higher dimensions.
problem Predicting Brownian motion on complex surfaces and higher dimensions.
method Developed new metrics (Uniform Drainage Metric) for surfaces and higher dimensions.
result Uniform Drainage Metric predicts Brownian motion's narrow escape time consistently.
Open manifolds with nonnegative Ricci curvature have virtually abelian fundamental groups if they escape from bounded balls at a small rate.
problem Understanding the fundamental groups of open manifolds with nonnegative Ricci curvature.
method Analyzing the escape rate of minimal geodesic loops and relating it to the fundamental group's properties.
result If an open manifold has a small escape rate, its fundamental group is virtually abelian.
SGD transitions between maxima and minima with varying time scales.
problem Understanding SGD's behavior near critical points in noisy landscapes.
method Analyzing SGD convergence and escape dynamics in 1D landscapes with infinite- and finite-variance noise.
result SGD reliably moves to the basin's minimum unless close to a local maximum, where it can linger.
The paper explores curvature-free effects in manifolds with volume growth and ends-counting.
problem Investigating curvature-free effects in manifolds with volume growth and ends-counting.
method Establishing two main theorems about volume growth and ends-counting.
result Proves the existence of smooth bounded mean-concave exhaustion and escaping geodesic lines.
Two-layer networks learn hard GLMs with SGD in high dimensions.
problem Learning hard generalized linear models with SGD in high-dimensional settings.
method Reduction of SGD dynamics to a stochastic process in lower dimensions, focusing on the role of stochasticity.
result Overparameterization enhances convergence by a constant factor, suggesting minimal role of stochasticity.
We study some potential theoretic properties of homothetic solitons Σn of the MCF and the IMCF. Using the analysis of the extrinsic distance function defined on these submanifolds in Rn+m, we observe similarities and differences in the geometry of solitons in both flows. In particular, we show that par…
We consider the Cauchy problem for the massive Dirac equation in the non-extreme Kerr-Newman geometry outside the event horizon. We derive an integral representation for the Dirac propagator involving the solutions of the ODEs which arise in Chandrasekhar's separation of variables. It is proved that for initial data in…
The paper analyzes neural network dynamics after weights escape the origin.
problem Understanding gradient flow dynamics of neural networks after the origin.
method Analyzes gradient flow of homogeneous neural networks with locally Lipschitz gradients.
result Characterizes the first saddle point encountered after escaping the origin.
Algorithm finds safe zones in policy Markov Decision Processes to limit trajectory escape.
problem Finding safe zones in policy Markov Decision Processes to limit trajectory escape.
method Bi-criteria approximation learning algorithm with polynomial sample complexity.
result Achieves almost 2 approximation for both escape probability and safe zone size.
This research explains why SGD generalizes better than ADAM in deep learning.
problem Understanding the generalization gap between SGD and ADAM in deep learning.
method Analyzing local convergence behaviors through Levy-driven stochastic differential equations (SDEs).
result SGD is more locally unstable and better escapes from sharp minima to flatter ones, leading to better generalization.
New algorithm helps escape saddle points in optimization problems.
problem Optimizing smooth non-convex functions to avoid saddle points.
method Perturbed Saddle-escape Descent (PSD) algorithm with explicit constants.
result PSD finds approximate second-order stationary points efficiently.
Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent recursions to efficiently escape saddle-points and reach second-order stationary p…
The paper proves Zimmer's conjecture for non-uniform lattices by controlling mass escape and Lyapunov exponents.
problem Proving Zimmer's conjecture for non-uniform lattices in higher-rank semisimple Lie groups.
method Establishes finiteness of low-dimensional actions, introduces novel techniques to control mass escape and Lyapunov exponents.
result Proves Zimmer's conjecture for many non-uniform lattices, improving previous results.
New methods help escape strict saddle points in nonsmooth optimization.
problem Escaping strict saddle points in nonsmooth optimization.
method An inexact stochastically perturbed gradient method applied to the Moreau envelope.
result A variety of algorithms for nonsmooth optimization can efficiently escape strict saddle points of the Moreau envelope.
New algorithm learns Koopman operator online, with complexity control and convergence guarantees.
problem Online learning of Koopman operator for general nonlinear systems.
method Sparse online learning via stochastic approximation, RKHS action, CME operator.
result Provably convergent algorithm with finite-time guarantees in mis-specified setting.
Deep ReLU networks escape from the origin via saddle points with a low-rank bias.
problem Understanding the dynamics of gradient descent in deep ReLU networks.
method Analysis of escape directions and singular values of weight matrices.
result The first singular value of the ℓ-th layer weight matrix is at least ℓ41 larger than any other singular value. We introduce an evolutionary algorithm called recombinator-k-means for optimizing the highly non-convex kmeans problem. Its defining feature is that its crossover step involves all the members of the current generation, stochastically recombining them with a repurposed variant of the k-means++ seeding algorithm. Th…
The Dirichlet random walk on manifolds has a positive escape rate if the cover is non-amenable.
problem Analyzing the stochastic behavior of Dirichlet random walks on manifolds.
method Defining a recursive process on Galoisian covers and proving a theorem about the escape rate.
result The escape rate is positive if and only if the cover is non-amenable.
We study robust distributed learning that involves minimizing a non-convex loss function with saddle points. We consider the Byzantine setting where some worker machines have abnormal or even arbitrary and adversarial behavior. In this setting, the Byzantine machines may create fake local minima near a saddle point tha…
Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics. Through investigating this …
New result on group actions in CAT(0) spaces with vanishing escape rate.
problem Understanding group actions with vanishing escape rate on CAT(0) spaces.
method Equivariant μ-harmonic map proof. result Existence of a flat subspace invariant under the action of Γ. In this paper, we propose a new adaptive stochastic gradient Langevin dynamics (ASGLD) algorithmic framework and its two specialized versions, namely adaptive stochastic gradient (ASG) and adaptive gradient Langevin dynamics(AGLD), for non-convex optimization problems. All proposed algorithms can escape from saddle poi…
PWGF escapes saddle points in nonconvex optimization.
problem Escaping saddle points in nonconvex optimization.
method PWGF uses noisy perturbations via Gaussian process to escape saddle points.
result PWGF achieves second-order optimality for nonconvex objectives.
The advancement of artificial intelligence has cast a new light on the development of optimization algorithm. This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for smooth non-convex functions. For the minimization phase, a model-driven deep lea…
New k-step policy gradient method avoids local optima in restricted policy classes.
problem Suboptimal local optima in policy gradient methods for restricted policy classes.
method Proposes a k-step policy gradient method to escape myopic local optima. result The method converges to near optimal solutions exponentially close to the optimal deterministic policy.
Theory explains deep nonlinear networks' plateaus and transitions.
problem Understanding long plateaus and feature acquisition transitions in deep nonlinear networks.
method Derived an exact identity for Frobenius norms, classified activation functions, and reduced matrix flow to a scalar ODE.
result Escape time law τ⋆=Θ(ε−(r−2)) for deep nonlinear networks, where r is the number of bottleneck layers. Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the first-order information. The existing analysis for algorithms using noise in the first-order information is quite involved and hides the es…
Hill-ADAM optimizes loss landscapes by exploring state space deterministically.
problem Escaping local minima in loss landscapes.
method Hill-ADAM alternates between minimizing and maximizing error to explore the loss space.
result Hill-ADAM finds the global minimum state in loss landscapes.
Nonconvex optimization algorithms with random initialization have attracted increasing attention recently. It has been showed that many first-order methods always avoid saddle points with random starting points. In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoi…
Study of SGD with state-dependent noise, improving escape from local minima.
problem Understanding and improving the dynamics of SGD in non-convex optimization.
method Formal study on SGD with state-dependent noise, proposing power-law dynamic with state-dependent diffusion.
result Power-law dynamic can escape from sharp minima exponentially faster than flat minima.
Based on our previous study [IS3] on the stationary scattering theory for the Schrodinger operator on a manifold possessing an escape function we complete our investigation by doing the time-dependent counterpart. A particular class of examples are manifolds with Euclidean and/or hyperbolic ends, possibly with unbounde…
A new method helps escape saddle points in non-convex optimization.
problem Escaping saddle points in non-convex optimization problems.
method CNC-SCSG method using a separate SGD step to help escape from strict saddle points.
result The method converges to a second-order stationary point with a rate of O(ε−2log(1/ε)). The paper analyzes how noise geometry influences the performance of SGD in machine learning.
problem Understanding how noise geometry affects the performance of stochastic gradient descent.
method Developed two metrics to quantify noise alignment strength and analyzed their effects on loss and subspace projection dynamics.
result Noise geometry can be used to guarantee alignment under certain conditions, aiding SGD's ability to escape from sharp minima.
We study the detailed path-wise behavior of the discrete-time Langevin algorithm for non-convex Empirical Risk Minimization (ERM) through the lens of metastability, adopting some techniques from Berglund and Gentz (2003. For a particular local optimum of the empirical risk, with an arbitrary initialization, we show tha…