arXiv research

CR-FM-NES improves NES for high-dimensional optimization.

Algorithm learns which weights to share in deep multi-task learning.

NES optimizes discrete structured VAEs effectively without gradient propagation.

We develop a more efficient NGD method for structured parameters.

This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms. NES maintains a parameterized distribution on the set of solution candidates, and the natural gradient is used to update th…

Investment strategies in financial markets can lead to instability due to market impacts.

PES method reduces bias in gradient estimation for unrolled graphs.

New method for portfolio management learns from past wealth evolution.

Since the debut of Evolution Strategies (ES) as a tool for Reinforcement Learning by Salimans et al. 2017, there has been interest in determining the exact relationship between the Evolution Strategies gradient and the gradient of a similar class of algorithms, Finite Differences (FD).(Zhang et al. 2017, Lehman et al. …

This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex functions. We try to motivate and derive the algorithm from intuitive concepts and …

Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead. Despite providing large improvements in wall-clock time, ES is data inefficient whe…

This project improves model robustness to affine transformations.

Algorithm improves vanilla option pricing accuracy during and before COVID-19.

AI simplifies trading strategies, potentially making markets more efficient.

NVA combines variational posteriors, annealing, and natural-gradient learning for multimodal optimization.

We analyze the sectoral dynamics of startup venture financing. Based on a dataset of 52000 start-ups and 110000 funding rounds in the United States from 2000 to 2017, and by applying both Principal Component Analysis (PCA) and Tensor Component Analysis (TCA) in sector space, we visualize and measure the evolution of th…

Variational Optimization forms a differentiable upper bound on an objective. We show that approaches such as Natural Evolution Strategies and Gaussian Perturbation, are special cases of Variational Optimization in which the expectations are approximated by Gaussian sampling. These approaches are of particular interest …

Model shows how heterogeneity in strategies and risk tolerance affects financial market stability.

We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the number of CPUs avail…

Gradients help find global optima in complex functions.

We propose a methodology for clustering financial time series of stocks' returns, and a graphical set-up to quantify and visualise the evolution of these clusters through time. The proposed graphical representation allows for the application of well known algorithms for solving classical combinatorial graph problems, w…

This paper explores the problem of unknotting closed braids and classical knots in mathematical knot theory. We apply evolutionary computation methods to learn sequences of moves that simplify knot diagrams, and show that this can be effective both when the evolution is carried out for individual knots and when a gener…

This version withdrawn by arXiv administrators because the submitter did not have the right to agree to our license at the time of submission.

ReSkill reconciles RL skill creation with policy optimization.

A new algorithm optimizes graph problems faster and more accurately.

ES-Single uses ES to estimate gradients in unrolled graphs, reducing variance and improving performance.

Study torsion parallel spinors on Lorentzian 4-manifolds and their evolution flows.

A new ES method improves reinforcement learning speed and accuracy.

Most decision tree induction algorithms are based on a greedy top-down recursive partitioning strategy for tree growth. In this paper, we propose several methods for induction of decision trees and their ensembles based on evolutionary algorithms. The main difference of our approach is using real-valued vector represen…

Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. Evolution relies on random mutations and on random genetic recombina…

Evolution Strategies (ES) are a powerful class of blackbox optimization techniques that recently became a competitive alternative to state-of-the-art policy gradient (PG) algorithms for reinforcement learning (RL). We propose a new method for improving accuracy of the ES algorithms, that as opposed to recent approaches…

Reproductive success and survival are influenced by wealth in human populations. Wealth is transmitted to offsprings and strategies of transmission vary over time and among populations, the main variation being how equally wealth is transmitted to children. Here we propose a model where we simulate both the dynamics of…

In this paper we introduce a new geometric flow --- the hyperbolic gradient flow for graphs in the $(n+1)$-dimensional Euclidean space $\mathbb{R}^{n+1}$. This kind of flow is new and very natural to understand the geometry of manifolds. We particularly investigate the global existence of the evolution of convex hypers…

New methods improve global optimisation for expensive functions using lookahead strategies.

We propose a new class of structured methods for Monte Carlo (MC) sampling, called DPPMC, designed for high-dimensional nonisotropic distributions where samples are correlated to reduce the variance of the estimator via determinantal point processes. We successfully apply DPPMCs to problems involving nonisotropic distr…

Study evolution equations on Lie groupoids using Fourier integral operators.

Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of human history. However, traditional techniques such as word representation learni…

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature. We use a first principles approach to explain LR and RP, and show a connection …

A model is presented of the market dynamics to emphasis the effects of increasing returns to scale, including the description of the born and death of the adaptive producers. The evolution of market structure and its behavior with the technological shocks are discussed. Its dynamics is in good agreement with some empir…

We present a dynamical model for the price evolution of financial assets. The model is based in a two level structure. In the first stage one finds an agent-based model that describes the present state of the investors' beliefs, perspectives or strategies. The dynamics is inspired by a model for describing predator-pre…

The numeraire portfolio in a financial market is the unique positive wealth process that makes all other nonnegative wealth processes, when deflated by it, supermartingales. The numeraire portfolio depends on market characteristics, which include: (a) the information flow available to acting agents, given by a filtrati…

ESAC combines genetic methods with RL to improve scalability and efficiency.

Study curves evolving on hypersurfaces with free boundaries, preserving length.

For a scalar evolution equation $u_t=K(t,x,u,u_x,\ldots, u_n), n\geq 2$ the cohomology spaces $H^{1,s}({\mathcal R}^\infty)$ vanishes for $s\geq 3$ while the space $H^{1,2}({\mathcal R}^\infty)$ is isomorphic to the space of variational operators. The cohomology space $H^{1,2}({\mathcal R}^\infty)$ is also shown to be …

Study on wealth and trading in PoS blockchain.

Theoretical model for iterative user discovery in recommender systems.

A new method for portfolio optimization using signature signatures to incorporate path-dependencies.

In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is desirable for modern training architectures; however, such methods typically req…