A new method learns disentangled macro actions from sequences for reinforcement learning.
problem Curse of dimensionality in reinforcement learning action space.
method Autonomously learns disentangled factor representation of actions to generate macro actions.
result Higher scores in complex environments compared to other reinforcement learning algorithms.
Paper optimizes Bayesian optimization for complex functions with macro-actions.
problem Optimizing complex, highly uncertain functions efficiently.
method Generalized GP upper confidence bound with macro-actions for scalable lookahead.
result Asymptotically optimal anytime variant of epsilon-Macro-GPO policy.
New approach improves black-box planning efficiency by discovering focused macros.
problem Difficulty of deterministic planning increases exponentially with depth.
method Discovering macro-actions with focused effects to improve goal-count heuristics.
result Focused macros dramatically improve black-box planning efficiency.
We prove that each coarsely homogenous separable metric space X is coarsely equivalent to one of the spaces: the sigleton, the Cantor macro-cube or the Baire macro-space. This classification is derived from coarse characterizations of the Cantor macro-cube and of the Baire macro-space given in this paper. Namely, we …
The paper tackles energy management in buildings with PCM using dynamic programming.
problem Optimal scheduling of HVAC systems in buildings with PCM is challenging due to nonlinear and non-convex characteristics.
method The paper uses dynamic programming to address the nonlinear nature of PCM, incorporating macro actions and multi-time scale Markov decision processes to reduce computational burden.
result The proposed method demonstrates a computational speed-up of up to 12,900 times compared to direct DP application.
Two different formulas for macro F1 lead to significant differences in classification evaluation.
problem Evaluation discrepancies in binary, multi-class, and multi-label classification problems.
method Comparison of two formulas for macro F1 metric.
result The two formulas can result in up to a 0.5 difference and different classifier rankings.
Aggregated variables can mask causal effects, turning unconfounded into confounded relations.
problem Aggregated variables can mask causal effects, leading to paradoxical confounding.
method Analysis of how aggregated variables can change the definition of causality and the feasibility of causal relations.
result Macro causal relations are defined by micro states, not just aggregated variables.
New method uses label-weighted conformal prediction for macro-coverage guarantees in classification.
problem Finding a balance between class-conditional and marginal coverage in long-tailed datasets.
method Label-weighted conformal prediction for macro-coverage guarantees.
result Validated prediction sets with macro-coverage guarantees on large-scale image datasets.
A novel method captures both micro- and macro-dynamics in temporal networks.
problem Capturing both micro- and macro-dynamics in temporal networks.
method Temporal Attention Point Process for micro-dynamics and a dynamics equation for macro-dynamics.
result Significantly outperforms state-of-the-arts in temporal tendency-related tasks.
HANET combines LSTM and attention mechanisms for better financial forecasting.
problem Lack of distinct macroeconomic regimes in financial datasets.
method Hierarchical Cross-Attention mechanism integrating long-run macro contexts with high-frequency market dynamics.
result HANET outperforms neural forecasters, especially during turbulent periods.
We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et al. (…
We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best…
Background and objective: Stacking is an ensemble machine learning method that averages predictions from multiple other algorithms, such as generalized linear models and regression trees. An implementation of stacking, called super learning, has been developed as a general approach to supervised learning and has seen f…
AG-RL uses action grammars to improve reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Integrates action grammars into reinforcement learning algorithms to enhance performance.
result Significant improvement in performance across multiple Atari games.
The study examines the generalization of Macro-AUC in multi-label learning, identifying label imbalance as a critical factor.
problem Theoretical understanding of Macro-AUC in multi-label learning is lacking.
method Characterization of generalization properties of learning algorithms based on surrogate losses w.r.t. Macro-AUC, identification of label imbalance as a critical factor.
result The widely-used univariate loss-based algorithm is more sensitive to label imbalance than pairwise and reweighted loss-based ones, implying worse performance.
LLM forecasting benchmarks suffer from information leakage, which confounds model performance.
problem LLM forecasting benchmarks suffer from information leakage.
method A retrieval-augmented LLM forecaster observes only decision-time information.
result The full pipeline obtains a median monthly Spearman rank IC of +0.154.
Paper introduces hierarchical softmax for global hierarchical classification tasks.
problem Improving classification accuracy in tasks with class hierarchies.
method Global hierarchical neural networks using hierarchical softmax.
result Hierarchical softmax outperforms regular softmax in multiple datasets.
Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For example, a person lifting a box can be imitated by a ceiling mounted robot or a desktop…
We study conditional risk minimization (CRM), i.e. the problem of learning a hypothesis of minimal risk for prediction at the next step of sequentially arriving dependent data. Despite it being a fundamental problem, successful learning in the CRM sense has so far only been demonstrated using theoretical algorithms tha…
Model predicts EU carbon prices using market and political factors.
problem Predict future carbon prices for EU market management.
method Support vector regression with grid search and cross validation.
result Model predicts carbon prices accurately for 2030.
GTSNE improves data visualization for high-dimensional data.
problem Visualizing high-dimensional data points in a 2D map.
method GTSNE is a variation of t-SNE that captures both local and macro structures.
result GTSNE produces better visualizations of high-dimensional data compared to other methods.
Selection mechanisms impact market volatility in evolving markets.
problem Determining how selection mechanisms affect market volatility in evolving markets.
method Used a population of evolving zero-intelligence agents and a frequent batch auction price-discovery mechanism to analyze the role of selection mechanisms.
result Local fitness-proportionate selection mechanisms correlate with high correlation between risk-aversion and volatility, while quantile-based selection mechanisms show less correlation.
In this paper, I discuss a method to tackle the issues arising from the small data-sets available to data-scientists when building price predictive algorithms that use monthly/quarterly macro-financial indicators. I approach this by training separate classifiers on the equivalent dataset from a range of countries. Usin…
Paper analyzes churn behavior in mobile games at micro and macro levels.
problem Understanding churn behavior in mobile games, especially at micro and macro levels.
method Developed a semi-supervised and inductive embedding model for micro-level churn prediction and constructed a relationship graph for macro-level churn ranking.
result Accurate micro-level churn prediction and macro-level churn ranking were achieved using novel techniques.
We discuss a Pareto macro-economy (a) in a closed system with fixed total wealth and (b) in an open system with average mean wealth and compare our results to a similar analysis in a super-open system (c) with unbounded wealth. Wealth condensation takes place in the social phase for closed and open economies, while it …
This paper analyses the relationship between BitCoin price and supply-demand fundamentals of BitCoin, global macro-financial indicators and BitCoin attractiveness for investors. Using daily data for the period 2009-2014 and applying time-series analytical mechanisms, we find that BitCoin market fundamentals and BitCoin…
MaMiC proposes a dual curriculum for robot manipulation tasks with sparse rewards.
problem Overcoming exploratory constraints in robot manipulation tasks with sparse rewards.
method Includes a macro curriculum scheme and a micro curriculum scheme to guide learning.
result Combining macro and micro curriculum strategies improves performance in robot manipulation tasks.
Crypto simulations show HODL strategy loads risk onto most investors, with macro-sentiment affecting returns.
problem Understanding real risk-return trade-offs and factors affecting crypto returns.
method Two independent analyses: 480 million Monte Carlo simulations and Bayesian multi-horizon local projection framework.
result HODL strategy exposes most investors to extreme downside risk, and macro-sentiment conditions are dominant indicators for future outcomes.
StarCraft II poses a grand challenge for reinforcement learning. The main difficulties of it include huge state and action space and a long-time horizon. In this paper, we investigate a hierarchical reinforcement learning approach for StarCraft II. The hierarchy involves two levels of abstraction. One is the macro-acti…
This paper presents a model of the dynamics of the wage income distribution.
Deep learning solves and estimates complex financial models.
problem Estimating and solving continuous-time financial models.
method Uses deep learning to solve and estimate models simultaneously.
result Demonstrates advantages like generality and large state space handling.
DISPR uses diffusion models to predict 3D cell shapes from 2D images.
problem Predicting 3D cell shapes from 2D microscopy images.
method Diffusion model trained to predict 3D shapes from 2D microscopy images as a prior.
result Adding DISPR predictions to minority cell classes improves classification accuracy.
The paper tackles multi-level fairness in algorithmic systems, addressing bias at both individual and structural levels.
problem Algorithmic systems can unfairly impact marginalized groups, especially when considering only individual-level bias.
method Formalizes multi-level fairness using causal inference tools, addressing effects of sensitive attributes at multiple levels.
result Illustrates the importance of accounting for macro-level sensitive attributes in fairness assessments.
Deep convolutional architecture identifies eye movements for biometric faster and more accurately.
problem Biometric identification of eye movements for authentication.
method Developed a deep convolutional architecture to process raw eye-tracking signals.
result Achieved a lower error rate by one order of magnitude and faster identification time by two orders of magnitude.
ART adapts class-wise resampling to improve imbalanced classification performance.
problem Class imbalance in classification tasks limits model performance.
method ART uses adaptive resampling based on class-wise performance metrics.
result ART consistently outperforms other methods on diverse benchmarks.
Unified model predicts stock and systemic risks from diverse financial data.
problem Isolating financial tasks leads to missed cross-scale dependencies.
method Shared Transformer backbone with modular task heads for cross-modal attention and multi-task optimization.
result Uni-FinLLM significantly outperforms baselines in stock forecasting, credit-risk assessment, and systemic-risk detection.
A new risk measure (FRM) for EM FI returns helps investors protect against volatility and policy instability.
problem Systemic risk in EM FI returns due to external shocks and domestic policy instability.
method Daily FRM-EM measure applied to 25 largest EM FI returns, incorporating Macro factors.
result FRM-EM captures systemic risk behavior in EM FI returns, reaching maximum during crises.
LLM generates coherent macroeconomic stress scenarios for portfolio risk assessment.
problem Macro-financial stress testing and portfolio risk assessment using traditional methods.
method Hybrid prompt-RAG pipeline combining structured prompting and retrieval of country fundamentals and news.
result LLM-generated scenarios yield stable tail-risk amplification with limited sensitivity to retrieval choices.
Bayesian framework improves trading robustness against market shifts.
problem Insufficient robustness and overfitting in trading models.
method Bayesian Robust Framework integrating macro-conditioned GAN and adversarial learning.
result Framework outperforms state-of-the-art models in diverse financial instruments.
LLMs add value in commodity portfolio construction when information set and implementation rules are held fixed.
problem Commodity portfolio construction
method Multi-Agent LLM Framework
result LLM strategies outperform Rule Agent in Sharpe terms
We show that an economic system populated by multiple agents generates an equilibrium distribution in the form of multiple scaling laws of conditional PDFs, which are sufficient for characterizing the probability distribution. The existence of the double scaling law is demonstrated empirically for the sales and the lab…
Study uses ML to predict currency and bond returns from news sentiment.
problem Predicting financial returns from news sentiment.
method Pretrained FinBERT model on finance-specific language, XGBoost classifier, SHAP for interpretability.
result XGBoost strategy outperforms benchmarks with Sharpe ratios > 5.
Hierarchical AI multi-agent framework optimizes equity portfolios in China's A-share market.
problem Optimizing equity portfolios in China's A-share market using AI and multi-agent systems.
method A hierarchical multi-agent design integrating macro, firm-level, and reinforcement learning approaches.
result Consistently outperforms benchmarks and state-of-the-art systems on risk-adjusted returns and drawdown control.
Paper uses LLMs for sector allocation, showing better returns.
problem Automated trading sector allocation inefficiencies.
method Systematic analysis of macroeconomic data and sentiment.
result LLM-based sector allocation outperforms traditional strategies.
New model improves DDI extraction with 78.5% macro F1-score.
problem Extracting Drug-Drug Interactions from text.
method Attention-Wrapped Hierarchical BLSTMs.
result Model outperforms state-of-the-art with macro F1-score of 0.785.
Model shows how relaxed leverage can lead to asset price bubbles.
problem Understanding how financial leverage affects asset prices and growth.
method Developed a macro-finance model with feedback loops between investment and land prices.
result Relaxed leverage can cause unbalanced growth and asset price bubbles.
Data analysis with log-periodical parametrization of the Brent oil price dynamics has allowed to estimate (very approximately) the date when the dashing collapse of the Brent oil price will achieve the absolute minimum level (corresponding to the so-called singularity point), after which there will occur a rather rapid…
Entropy helps explain disorder in both macro and micro systems.
problem Connecting macro and micro systems with entropy analysis.
method Analyzing entropy from both macroscopic and microscopic perspectives.
result Entropy measures disorder in both macroscopic and microscopic systems.