Stochastic Gradient Descent finds wide but shallow minima due to undersampling, akin to energy-entropy competition.
problem The empirical effectiveness of Stochastic Gradient Descent in machine learning.
method Deriving a correspondence between parameter inference and free energy minimisation in statistical physics, where the degree of undersampling plays the role of temperature.
result Stochasticity in Stochastic Gradient Descent biases it towards wide minima, explaining its empirical effectiveness.
Proposes a new acquisition function for batched Bayesian optimization.
problem Intractability of acquisition functions for batched Bayesian optimization.
method Statistical physics inspired acquisition function for Gaussian processes.
result Demonstrates competitive performance on various problems.
We introduce a pathwise approach to analyze the relative performance of an equity portfolio with respect to a benchmark market portfolio. In this energy-entropy framework, the relative performance is decomposed into three components: a volatility term, a relative entropy term measuring the distance between the portfoli…
Reinforcement learning for continuous-time risk-sensitive asset allocation
problem Continuous-time risk-sensitive asset allocation
method Free energy-entropy duality reformulation and q-learning actor-critic method result Optimal policy learning with high accuracy
Solves risk-sensitive investment via duality, entropic regularization, and RL.
problem Risk-sensitive portfolio management in a factor-based setting.
method Free energy-entropy duality, Kuroda-Nagai change-of-measure, RL algorithm.
result Direct analytical solution, explicit controls, two interpretations of optimal allocation.
The paper introduces a new system of equations for Hessian-cscK metrics.
problem Finding constant scalar curvature Kähler metrics.
method Proposes a coupled system of complex Hessian equations and shows it can be variational.
result Proves a C0-estimate for the system that depends on entropy. We explore a new method for discrete-time control problems using randomization and entropy.
problem Discrete-time linear-exponential quadratic Gaussian (LEQG) control problem.
method Introduce exploration through randomization and apply duality between free energy and relative entropy.
result Reduced LEQG problem to equivalent risk-neutral LQG control problem with entropy regularization.
Paper introduces a new method for risk-sensitive investment management using RL.
problem Risk-sensitive portfolio management with unknown model parameters.
method Combines RL and risk-sensitive stochastic control with Gaussian perturbations for exploration.
result Endogenous relative-entropy regularization and optimal investment strategy derived.
Wavelet analysis reveals financialization effects on oil-food price correlation.
problem Investigating the correlation between oil and food prices and their determinants.
method Wavelet analysis and energy-based measures to differentiate high and low frequency movements.
result Significant local correlation between food and oil is due to financialization and emerging economies' demand.
Proposes CoPO, a new policy optimization method for competitive games.
problem Designing efficient optimization methods for competitive Markov decision processes.
method Competitive policy optimization (CoPO) approach that exploits game-theoretic nature of competitive games.
result Stable optimization, convergence to sophisticated strategies, and higher scores compared to baseline methods.
Kaggle competitions offer valuable insights for business forecasting.
problem Lack of attention to Kaggle competitions in academic forecasting studies.
method Review of results from six Kaggle competitions featuring real-life business forecasting tasks.
result Global ensemble models outperform local single models in Kaggle competitions.
The origin of economic crises is a key problem for economics. We present a model of long-run competitive markets to show that the multiplicity of behaviors in an economic system, over a long time scale, emerge as statistical regularities (perfectly competitive markets obey Bose-Einstein statistics and purely monopolist…
New framework promotes reproducible, domain-agnostic reinforcement learning algorithms.
problem Domain-specific, compute-resource-maximizing, and non-reproducible participant solutions in reinforcement learning competitions.
method Submission retraining, domain randomization, desemantization through domain obfuscation, and compute/environment-sample budget limitation.
result Participant submissions are reproducible, non-specific to the competition environment, and sample/resource efficient.
The real estate is a pillar industry of China's national economy. Due to changes in policy and market conditions, the real estate companies are facing greater pressures to survive in a competitive environment. They must improve their financial competitiveness. Based on the conceptual framework of financial competitiven…
Google Brain competition on adversarial attacks and defenses.
problem Developing methods to generate and defend against adversarial examples.
method Organized a competition to encourage new adversarial attack and defense methods.
result Several top teams developed innovative methods in adversarial attacks and defenses.
First ABAW 2020 Competition analyzes affective behavior tasks.
problem Automatic analysis of valence-arousal, basic expressions, and action units in real-world scenarios.
method Provided Aff-Wild2 database, described Challenges, evaluation metrics, and top-performing systems.
result Demonstrated the feasibility of automatic affective behavior analysis in real-world settings.
Study examines machine learning competitions' impact on AI development.
problem Fostering innovation and skill development in AI.
method Analysis of major competition platforms, workflows, and participant demographics.
result MLCs promote collaboration, reproducibility, and continuous innovation in AI.
Bayesian rating system for large competitions improves prediction and efficiency.
problem Rating systems for large, competitive events like online programming contests.
method Developed a Bayesian rating system for many participants, proving robustness and runtime.
result The system outperforms existing systems in accuracy and computation speed.
MineRL Competition reduced reinforcement learning sample needs.
problem Sample inefficiency in reinforcement learning.
method Human demonstrations and imitation learning integrated into reinforcement learning algorithms.
result Top solutions used deep reinforcement learning and imitation learning.
This paper evaluates financial competitiveness of Indian real estate companies using entropy method.
problem Improving financial competitiveness of Indian real estate companies in a competitive market.
method Financial competitiveness evaluation index system using key financial ratios and a scoring system.
result Companies with high scores have strong profitability and operational capacity, while those with lower scores struggle with solvency and working capital.
Arena model predicts competition outcomes without rating many individuals.
problem Predicting competition outcomes without extensive individual ratings.
method Parametric arena model exploiting competition structure and uncertainty quantification.
result Invariant Bayes estimator and consistent uncertainty estimations.
Paper tackles online optimization with memory and competitive control.
problem Minimizing hitting and switching costs in online optimization problems.
method Optimistic Regularized Online Balanced Descent algorithm.
result Achieves a constant, dimension-free competitive ratio.
This paper offers advice for designing and analyzing data competitions.
problem Overfitting in data competitions can limit the learning outcomes.
method Strategic design of data sets and post-competition analysis using GLMs.
result Richer and more informative summaries enhance the interpretation of results.
In this paper, the optimal pricing strategy in Avellande-Stoikov's for a monopolistic dealer is extended to a general situation where multiple dealers are present in a competitive market. The dealers' trading intensities, their optimal bid and ask prices and therefore their spreads are derived when the dealers are info…
Study competitive agents' optimal consumption and investment strategies with relative performance criteria.
problem Optimizing consumption and investment strategies for multiple agents with relative performance considerations.
method Derived a closed-form solution for an n-player game and mean field game, analyzing the impact of risk tolerance and competitiveness parameters. result Unique equilibria found, showing nonlinear and non-monotone dependence on agents' risk tolerance and competitiveness parameters.
Model predicts growth competition on curved surfaces.
problem Growth dynamics of two subsets on Riemannian manifolds.
method Modeling growth rates on spherically symmetric Riemannian manifolds.
result Conditions for bounded or unbounded growth on different manifolds.
Market competition depends on computational complexity, P != NP makes it impossible.
problem Competitive market outcomes require computational intractability.
method Analyzes the computational hardness of collusion detection in markets.
result If P != NP, collusion detection is computationally infeasible, making collusion unstable.
The M5 competition tackles overdispersed retail sales forecasting with GAMLSS.
problem Overdispersed and zero-inflated retail sales data.
method Distributional forecasting using GAMLSS framework.
result GAMLSS provides better probabilistic forecasting for count data.
Model predicts competition between similar products in sales.
problem Predicting cannibalization between similar products in sales.
method Developed a neural network model that computes a 'competitiveness' function based on product features.
result The model outperforms traditional methods in predicting market share.
Improved forecasting in daily time series competition using a correlator method.
problem Forecasting daily time series with data leakage issues.
method Ensemble of five statistical forecasting methods and a correlator method.
result The correlator method was responsible for most of the gains over naive forecasting.
Proxy measures in competitive systems lead to corruption and inefficiency.
problem Corruption of proxy measures in competitive systems.
method Agent-based model integrating insights from complex systems, contest theory, behavioral economics, and cultural evolution.
result Proxy measures lead to corruption and convergence towards an equilibrium level of corruption.
Politicians world-wide frequently promise a better life for their citizens. We find that the probability that a country will increase its {\it per capita} GDP ({\it gdp}) rank within a decade follows an exponential distribution with decay constant λ=0.12. We use the Corruption Perceptions Index (CPI) and the Global …
We introduce an irreversible discrete multiplicative process that undergoes Bose-Einstein condensation as a generic model of competition. New players with different abilities successively join the game and compete for limited resources. A player's future gain is proportional to its ability and its current gain. The the…
The study assesses how market competitiveness affects electricity price forecasting.
problem Impact of market competitiveness on electricity price estimation.
method Used a multi-layer perception model with back propagation and Levenberg-Marquardt mechanism, incorporating market power indices and other variables.
result Market power indices enhance forecasting accuracy of daily electricity prices.
We present a broad agenda for meaningful banking regulation reform aiming the creation of evolutive competitive environment to maximize the effectiveness of international financial system through the introduction of fair competition process among the banks in free market capitalism. We assume that the international fin…
FLAIR measures LP competitiveness in AMMs, improving LP performance evaluations.
problem LP returns are affected by both market risk and competitive strategies.
method Introduces FLAIR metric to quantify LP competitiveness and assesses its impact on LP returns.
result FLAIR captures dynamic behavior of LPs and differentiates between active provisioning strategies.
New algorithm for top-K ranking with linear time and competitive ratio of sqrt(n).
problem Identifying top K items from noisy pairwise comparisons.
method Linear time algorithm with competitive ratio of sqrt(n) under strong stochastic transitivity model.
result Tight competitive ratio of sqrt(n) for top-K ranking problem.
Kaggle chronicles 15 years of competitions, innovation, and data science.
problem Exploring 15 years of data science competitions and innovations.
method Longitudinal trend analysis and exploratory data analysis of millions of kernels and discussion threads.
result Kaggle is a growing platform with diverse use cases and adaptable Kagglers.
A competition increases financial transaction models' robustness against attacks.
problem Neural networks used by banks are vulnerable to adversarial attacks in financial transaction data.
method A novel competition where participants propose attacks and defenses, simulating real-world conditions.
result Participants' strategies and outcomes provide insights into improving financial transaction models' robustness.
This work bridges competitive learning with gradient-based learning for faster feature extraction.
problem Lack of powerful feature extractors in competitive learning methods.
method Introduces gradient-based competitive layers for feature extraction.
result Demonstrates theoretical equivalence and faster convergence of gradient-based competitive layers.
Study predicts individual treatment effects in ride-sharing competitions.
problem Understanding how team competitions affect individual drivers' outcomes.
method Analyzed data from 500 competitions, built machine learning models.
result Reduced out-sample prediction error by over 24%.
Two-layer model studies reinsurance contracts and competition between insurer and reinsurers.
problem Modeling and analyzing reinsurance contracts and competition between insurer and reinsurers.
method Two-layer stochastic game model with insurer negotiating with reinsurers, and reinsurers competing for business.
result Existence and uniqueness of equilibrium strategies for the insurer and reinsurers, characterized in semiclosed form.
ViZDoom competition tests AI in Doom using only visual input.
problem Creating AI bots that play Doom effectively from raw visual data.
method Multi-player deathmatch in Doom; bots make decisions based on screen buffer.
result Reinforcement learning can produce capable bots but not competitive against humans.
Indirect competition emerged from the complex organization of human societies, and knowledge of the existing network topology may aid in developing effective strategies for success. Here, we propose an agent-based model of competition with systems co-existing in a `small-world' social network. We show that within the r…
Review of acoustic scene classification methods in a competition.
problem Categorizing audio sequences into classes based on spectral content.
method Competition involving students and external participants, ablation study, neural network baseline comparison.
result Improved classification over neural network baseline.
The paper analyzes optimal stock position-building strategies in competitive markets.
problem Optimal stock position-building in competitive markets with market impact.
method Developed a game-theoretic framework to find best-response strategies.
result Closed-form solutions for equilibrium trading strategies were derived.
Replication confirms CGD's effectiveness in competitive games.
problem Reproducibility of a novel Nash equilibrium algorithm.
method Replicated experiments and provided Python implementation.
result CGD avoids oscillatory and divergent behaviours.
Proposes new genetic algorithm rule for market competition.
problem Market competition genetic algorithm rules.
method Econophysics kinetic market model as an evolutionary algorithm.
result New replacement rule for genetic algorithms.