The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies …
On-device research index
arXiv research
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “step function”
This paper provides a block coordinate descent algorithm to solve unconstrained optimization problems. In our algorithm, computation of function values or gradients is not required. Instead, pairwise comparison of function values is used. Our algorithm consists of two steps; one is the direction estimate step and the o…
Researchers describe Casimir functions for 3- and 4-step nilpotent Lie groups.
problem Understanding Casimir functions for free nilpotent Lie groups of steps 3 and 4.
method Construction of Casimir functions for free nilpotent Lie groups of steps 3 and 4.
result For 3-step groups, coadjoint orbits are fully described as affine subspaces or direct products of quadrics.
Random Function Descentmath.OC
Random Function Descent improves optimization in high dimensions.
problem Lack of effective optimization methods in high-dimensional spaces.
method Introducing a 'random function' framework to optimize classical optimization problems.
result Random Function Descent (RFD) is a scalable optimization method that bridges Bayesian and classical optimization.
Paper develops an online learning algorithm for functional data models.
problem Recovering slope functions or predictors in functional data models.
method Online regularized learning algorithm in reproducing kernel Hilbert spaces with polynomially decaying step-size.
result Established fast convergence rates for estimation error without capacity assumption.
Polyak step size GD reaches final radius of convergence after log iterations.
problem Statistical and computational complexities of Polyak step size GD.
method Generalized smoothness and Lojasiewicz conditions, stability of gradients.
result Polyak step size GD reaches final statistical radius of convergence after logarithmic number of iterations.
FHBI enhances generalization in Bayesian inference with iterative steps in functional spaces.
problem Improving generalization in Bayesian inference models.
method Iterative two-step procedure with adversarial and functional descent steps in a reproducing kernel Hilbert space.
result FHBI consistently outperforms nine baseline methods on the VTAB-1K benchmark.
Exchangeable graphs arise via a sampling procedure from measurable functions known as graphons. A natural estimation problem is how well we can recover a graphon given a single graph sampled from it. One general framework for estimating a graphon uses step-functions obtained by partitioning the nodes of the graph accor…
The Douglas Rachford algorithm is an algorithm that converges to a minimizer of a sum of two convex functions. The algorithm consists in fixed point iterations involving computations of the proximity operators of the two functions separately. The paper investigates a stochastic version of the algorithm where both funct…
As a popular meta-learning approach, the model-agnostic meta-learning (MAML) algorithm has been widely used due to its simplicity and effectiveness. However, the convergence of the general multi-step MAML still remains unexplored. In this paper, we develop a new theoretical framework to provide such convergence guarant…
Efficiently optimizes expensive functions with multi-step lookahead using one-shot optimization.
problem Optimizing expensive functions with long-term impacts using myopic approaches.
method Formulated as nested optimization problems within a multi-step scenario tree, optimized in one-shot fashion.
result Multi-step expected improvement is computationally tractable and outperforms existing methods.
A new machine learning method for Bayesian inverse problems in function spaces.
problem Bayesian inverse problems in function spaces with incompatibility of white noise sources.
method One-step generative transport with amortized neural operator and prior-aligned Gaussian random field.
result Generative operator trained on prior samples and noisy observations generates posterior samples efficiently.
Proposes an exponentially increasing step-size for faster parameter estimation in statistical models.
problem Slow convergence of gradient descent in locally convex loss functions.
method Exponentially increasing step-size in gradient descent algorithm.
result Converges linearly to optimal solution under homogeneous assumptions.
New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.
problem Challenges in online reinforcement learning for non-episodic, finite-horizon MDPs.
method Introduces a K-step lookahead Q-function with a time-varying threshold for selecting actions.
result Achieves minimax optimal constant regret for K=1 and regret for K ≥ 2.
Stochastic algorithm achieves sublinear convergence for bi-objective optimization.
problem Optimizing two conflicting functions using gradient or subgradient descent.
method Stochastic alternating algorithm with varying steps for each objective.
result Achieves sublinear convergence rate of O(1/T) under strong convexity.
A new Bayesian method optimizes time-dependent expensive functions with lookahead.
problem Maximizing a time-dependent, expensive oracle with limited evaluations.
method Recursive, two-step lookahead expected payoff (r2LEY) acquisition function.
result r2LEY outperforms myopic methods in synthetic and real-world datasets.
We propose a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent applied to the problem of minimizing a strongly convex composite function represented as the sum of an average of a large number of smooth convex functions, and simple nonsmooth conve…
The main goal of this work is equipping convex and nonconvex problems with Barzilai-Borwein (BB) step size. With the adaptivity of BB step sizes granted, they can fail when the objective function is not strongly convex. To overcome this challenge, the key idea here is to bridge (non)convex problems and strongly convex …
Deep Portfolio Theoryq-fin.PM
We construct a deep portfolio theory. By building on Markowitz's classic risk-return trade-off, we develop a self-contained four-step routine of encode, calibrate, validate and verify to formulate an automated and general portfolio selection process. At the heart of our algorithm are deep hierarchical compositions of p…
A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learningcs.LG
The paper introduces a multi-step loss function to improve model-based reinforcement learning.
problem Compounding of one-step prediction errors in long trajectories.
method A multi-step objective function combining MSE losses at various future horizons.
result Models trained with the multi-step loss achieve significant improvement in future prediction.
The purpose of this paper is to present the first continuous families of Riemannian manifolds isospectral on functions but not on 1-forms, and simultaneously, the first continuous families of Riemannian manifolds with the same marked length spectrum but not the same 1-form spectrum. The examples presented here are Riem…
The paper tackles noisy combinations of continuous and step functions, providing conditions for their identification.
problem Recovering noisy observations as a combination of continuous and step functions.
method Topological and local properties of the functions are used to determine conditions for identification. A practical estimation algorithm is provided.
result Conditions for the identification of continuous and step functions based on their global and local properties.
Stochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for tuning the step sizes have been proposed, ranging from coordinate-wise approach…
Stochastic (sub)gradient methods require step size schedule tuning to perform well in practice. Classical tuning strategies decay the step size polynomially and lead to optimal sublinear rates on (strongly) convex problems. An alternative schedule, popular in nonconvex optimization, is called \emph{geometric step decay…
Learning the Step-size Policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Algorithmcs.LG
Proposes a neural network for learning step-size policies for L-BFGS optimization.
problem Optimizing step sizes for L-BFGS in large-scale problems.
method Neural network architecture using local iterate information, trained via stochastic optimization.
result Outperforms existing step size selection methods in training classifiers.
Method learns graphons from graphs via Gromov-Wasserstein barycenters.
problem Learning nonparametric graph models from finite graphs.
method Approximate graphons with step functions, use Gromov-Wasserstein distance, learn barycenters.
result Proposed method outperforms state-of-the-art on synthetic and real-world data.
In order to decode the human brain, Multivariate Pattern (MVP) classification generates cognitive models by using functional Magnetic Resonance Imaging (fMRI) datasets. As a standard pipeline in the MVP analysis, brain patterns in multi-subject fMRI dataset must be mapped to a shared space and then a classification mod…
W-Flow generates images in one step, faster and better than multi-step methods.
problem Efficiently generating images from a simple reference distribution to a target data distribution.
method W-Flow uses Wasserstein gradient flows to transform the reference distribution to the target distribution in a single step, trained with Sinkhorn divergence.
result W-Flow achieves state-of-the-art results in ImageNet 256256 generation with improved mode coverage and faster sampling.
We propose mS2GD: a method incorporating a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent (S2GD). We consider the problem of minimizing a strongly convex function represented as the sum of an average of a large number of smooth convex function…
Paper uses RL to optimize daily step distribution for better health biomarkers.
problem Lack of personalized PA distribution recommendations for health biomarkers.
method Developed an offline reinforcement learning algorithm to learn optimal PA distributions.
result Learned optimal policy suggests more consistent daily steps and tailored recommendations.
New tests for VaR and ES forecast encompassing using flexible link functions.
problem Testing forecast encompassing for Value at Risk and Expected Shortfall.
method Flexible link functions for testing convex forecast combinations and nonstandard asymptotic theory for boundary parameters.
result Tests based on new link functions outperform unrestricted linear link functions for one-step and multi-step forecasts.
Automatic, Dynamic, and Nearly Optimal Learning Rate Specification by Local Quadratic Approximationstat.ML
A new method automatically and dynamically sets learning rates in deep learning.
problem Determining the appropriate learning rate in deep learning tasks is challenging and often subjective.
method Local Quadratic Approximation (LQA) to automatically and dynamically set learning rates.
result The proposed method leads to nearly optimal learning rates in a computationally efficient way.
Proposes SD-KDE for density estimation using debiased kernel density with score-based adjustments.
problem Density estimation with bias in kernel density estimation.
method Adjusts data points by taking a step along the estimated score function, then applies standard KDE with modified bandwidth.
result Significantly reduces mean integrated squared error compared to standard Silverman KDE, especially with noisy score function estimates.
The paper extends risk measures to two-step approximations and studies log-concave distributions.
problem Extending classical risk measures to two-step approximations.
method Optimization problem for determining optimal regime thresholds and values for log-concave distributions.
result Conditions for the uniqueness of regime changing in log-concave distributions.
Community detection in hypergraphs is explored. Under a generative hypergraph model called "d-wise hypergraph stochastic block model" (d-hSBM) which naturally extends the Stochastic Block Model from graphs to d-uniform hypergraphs, the asymptotic minimax mismatch ratio is characterized. For proving the achievability, w…
Method learns neural network to overestimate reference function with guarantees.
problem Learning a neural network to overestimate a reference function on a given domain.
method Two-step process: constructing Majoring Points and optimizing a neural network.
result The learned neural network overestimates the reference function on the domain.
Signature functions of knotsmath.GT
The signature function of a knot is an integer-valued step function on the unit circle in the complex plane. Necessary and sufficient conditions for a function to be the signature function of a knot are presented.
We propose a novel Bayesian approach to solve stochastic optimization problems that involve finding extrema of noisy, nonlinear functions. Previous work has focused on representing possible functions explicitly, which leads to a two-step procedure of first, doing inference over the function space and second, finding th…
Speed learning on the flymath.OC
The practical performance of online stochastic gradient descent algorithms is highly dependent on the chosen step size, which must be tediously hand-tuned in many applications. The same is true for more advanced variants of stochastic gradients, such as SAGA, SVRG, or AdaGrad. Here we propose to adapt the step size by …
Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and outputs the next state---a one-step model. This model can be composed with itse…
Introduces a new length functional for Ricci flow to detect steady solitons.
problem Detecting steady solitons in Ricci flow.
method Develops a modified length functional and shows it satisfies differential inequalities.
result The length functional generates a distance function that saturates on steady soliton manifolds.
New -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 -step policy gradient method to escape myopic local optima.
result The method converges to near optimal solutions exponentially close to the optimal deterministic policy.
The paper develops methods for causal function estimation and inference with multiway clustered data.
problem Estimation and inference for causal functions under multiway clustering.
method Two-step procedure using machine learning for nuisance parameters and projection onto basis functions.
result Rejects the null hypothesis of uniformly zero effects and reveals heterogeneous treatment effects.
Three-hidden-layer neural networks can approximate Hölder continuous functions uniformly with exponential rate.
problem Approximating Hölder continuous functions with neural networks.
method Introduced Floor-Exponential-Step (FLES) networks with three hidden layers.
result Uniform approximation of Hölder continuous functions with an exponential rate.
Estimates variance function using aggregation methods in regression models.
problem Estimating variance function in regression models.
method Two-step procedure involving model selection or convex aggregation, using two independent samples.
result Consistency of the proposed method in L2 error for MS and C aggregations.
New embedding method in function spaces improves expressiveness.
problem Enhancing expressiveness in knowledge graph embeddings.
method Employing polynomial functions and neural networks with varying layer complexities.
result Improved expressiveness and more degrees of freedom in entity representation.
New adaptive step-size method for convex optimization without tuning.
problem Optimizing convex functions efficiently with stochastic gradients.
method Adapted Adaptive Gradient Descent Without Descent to stochastic setting.
result Stochastic gradient descent converges under various assumptions.
We consider the dynamics of a linear stochastic approximation algorithm driven by Markovian noise, and derive finite-time bounds on the moments of the error, i.e., deviation of the output of the algorithm from the equilibrium point of an associated ordinary differential equation (ODE). We obtain finite-time bounds on t…