This paper uses decolonial theory to improve AI's ethical development.
problem AI's risks to vulnerable peoples and negative impacts of innovation.
method Embedding decolonial critical approach in AI technical practice.
result Developing tactics to align AI with ethical principles.
The study redefines algorithmic fairness as a sociotechnical concept.
problem Systemic discrimination in automated decision-making.
method Literature review and sociotechnical analysis.
result Algorithmic fairness should be viewed through a sociotechnical lens.
New method improves meta-reinforcement learning efficiency.
problem Sample inefficiency in meta-reinforcement learning.
method Hindsight Foresight Relabeling (HFR) method.
result HFR improves performance on various meta-reinforcement learning tasks.
ADR helps LLMs find and use historical analogies for foresight analysis.
problem LLMs struggle to find relevant historical analogies due to surface-level matching.
method Proposes CANA framework with mechanism alignment and cross-analogy confirmation.
result CANA improves historical analogy generation by up to 10%.
Suppose you have one unit of stock, currently worth 1, which you must sell before time T. The Optional Sampling Theorem tells us that whatever stopping time we choose to sell, the expected discounted value we get when we sell will be 1. Suppose however that we are able to see a units of time into the future, and ba…
VFDS selects dynamic features for efficient HAR tasks, optimizing performance-cost trade-offs.
problem Optimizing feature selection for varying costs and dynamic contexts in machine learning tasks.
method Bayesian learning framework with variational dynamic selection policy.
result VFDS selects different features under changing contexts, saving sensory costs while maintaining HAR accuracy.
Foresight Arena benchmarks AI forecasting on real-world markets, isolating predictive edge.
problem Evaluating AI forecasting ability in real-world markets is challenging due to overfitting, centralized trust, and conflated metrics.
method Permissionless, on-chain benchmark using probabilistic forecasts, commit-reveal protocol, and smart contracts.
result Demonstrates the need for 350 predictions to reliably distinguish agents of different skill levels.
Financial asset markets are sociotechnical systems whose constituent agents are subject to evolutionary pressure as unprofitable agents exit the marketplace and more profitable agents continue to trade assets. Using a population of evolving zero-intelligence agents and a frequent batch auction price-discovery mechanism…
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor s…
ARL bridges non-Markovian decision processes with reinforcement learning, improving foresight and stability.
problem Inaccurate foresight in non-Markovian environments due to state-based methods' limitations.
method Lifted state space into a signature-augmented manifold, using a self-consistent field approach to anticipate future path-law.
result ARL achieves deterministic evaluation of expected returns with reduced computational complexity and variance.
FRONT optimizes decisions with interference, reducing regret over time.
problem Short-sighted policies in online decision-making due to ignoring interference.
method FRONT considers long-term impacts of decisions, using exploratory and exploitative strategies.
result FRONT achieves sublinear regret in both immediate and consequential impacts.
We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information in hindsight, rathe…
We show that a trader, who starts with no initial wealth and is not allowed to borrow money or short sell assets, is theoretically able to attain positive wealth by continuous trading, provided that she has perfect foresight of future asset prices, given by a continuous semimartingale. Such an arbitrage strategy can be…
Online social networks offer a new way to investigate financial markets' dynamics by enabling the large-scale analysis of investors' collective behavior. We provide empirical evidence that suggests social media and stock markets have a nonlinear causal relationship. We take advantage of an extensive data set composed o…
Study finds significant price declines and capital reallocation from centralized to decentralized exchanges after FTX collapse.
problem Quantifying trust dynamics and redistribution between centralized and decentralized exchanges.
method Interdisciplinary approach combining causal inference and computational text analysis.
result Significant price declines and capital reallocation from centralized to decentralized exchanges following the FTX collapse.
This article is a follow-up of a short essay that appeared in Nature 455, 1181 (2008) [arXiv:0810.5306]. It has become increasingly clear that the erratic dynamics of markets is mostly endogenous and not due to the rational processing of exogenous news. I elaborate on the idea that spin-glass type of problems, where th…
Methodology explores fairness limits in decision tree classifiers.
problem Understanding statistical limits of bias mitigation in machine learning.
method Multi-objective framework optimizing accuracy and fairness.
result Decision tree models can be optimized for fairness with minimal accuracy loss.
Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives. Therefore, just like for power plants, highways, and myriad other engineered sociotechnical systems, we must consider the safety of systems involving machine learning. In this paper, we first …
Accelerates policy optimization in RL with optimistic and adaptive updates.
problem Improving policy optimization methods in reinforcement learning.
method Integrates foresight into policy improvement step via optimistic and adaptive updates.
result Designs an optimistic policy gradient algorithm, adaptive via meta-gradient learning.
New method combines heuristics and search techniques to speed up cooperative planning for autonomous vehicles.
problem Efficient cooperative planning for autonomous vehicles in complex traffic scenarios.
method Combining learned heuristics with Monte Carlo Tree Search (MCTS) to guide search towards promising actions.
result Better solutions at lower computational costs achieved through accelerated planning.
Listing on the Dow Jones Sustainability Index is seen as a gold-standard, verifying to the market that a firm is fully engaged with a corporate social responsibility agenda. Robustly quantifying the impact of listing, and de-listing, against any industry level shocks, as well as evolution in the competitive relationshi…
Study uses neural networks to predict credit risk in banks.
problem Credit risk management in commercial banks.
method Backpropagation neural network model.
result Neural network model improves credit risk prediction.
The article reviews key contributions to hyperspectral unmixing.
problem Improving hyperspectral unmixing algorithms.
method Exploring and analyzing existing algorithms like VCA, SISAL, and DECA.
result DECA shows potential for further development and has hidden connections with SISAL.
Interactive weak supervision learns useful heuristics from user feedback.
problem Creating useful heuristics for large labeled datasets is tedious and subjective.
method Develops an interactive framework for learning heuristics from user feedback.
result Only a few feedback iterations are needed to train models without ground truth labels.
New method prevents RLHF alignment collapse by accounting for policy's influence on reward model updates.
problem Iterative RLHF leads to alignment collapse where policies exploit RM's blind spots.
method Foresighted policy optimization (FPO) restores missing steering term via regularization.
result FPO prevents alignment collapse on LLM alignment pipelines using Llama-3.2-1B.
LEXA learns to discover and achieve goals in unseen environments.
problem Learning to solve diverse tasks in complex visual environments without supervision.
method LEXA learns a world model from image inputs and uses it to train an explorer and an achiever policy from imagined rollouts.
result LEXA solves tasks specified as goal images zero-shot without additional learning.
Study when to replace machine learning models with new data.
problem When to switch machine learning models with new data sources.
method Unified economic and statistical framework linking learning-curve dynamics, data-acquisition, and retraining costs.
result Look-ahead sequential method outperforms other methods and approaches optimal value.
By observing their environment as well as other traffic participants, humans are enabled to drive road vehicles safely. Vehicle passengers, however, perceive a notable difference between non-experienced and experienced drivers. In particular, they may get the impression that the latter ones anticipate what will happen …
Paper optimizes battery storage in multiple energy markets for better profits.
problem Optimizing battery storage participation in multiple energy markets to balance supply and demand.
method Developed a joint bidding strategy combining intraday and frequency markets using mixed integer linear programming and a learned classifier strategy.
result The LCS increases overall profits by over 4% compared to static strategies and by more than 3% over a naive dynamic benchmark.
Study examines impact of fairness penalties on clinical risk prediction models.
problem Widespread health disparities in machine learning-guided clinical decision-making.
method Empirical study across multiple databases, outcomes, and sensitive attributes.
result Penalizing fairness violations nearly universally degrades model performance and fairness metrics.
Paper explains DRL strategies for portfolio management using linear models.
problem Difficulty in understanding DRL-based trading strategies.
method Empirical approach using linear models and integrated gradients.
result DRL agents show stronger multi-step prediction power than machine learning methods.
NTK-SAP improves neural network pruning by aligning training dynamics.
problem Improving neural network pruning to reduce training time and memory.
method Prune connections based on the spectrum of the Neural Tangent Kernel (NTK), using multiple random weight realizations and random inputs.
result Empirically, NTK-SAP achieves better performance than all baselines on multiple datasets.
Develops a new trading strategy for renewable producers to manage price volatility.
problem Price volatility and imbalance risk in power markets due to renewable generation.
method Data-driven continuous-time stochastic optimal control framework using SDEs and diffusion models.
result Trading strategy outperforms benchmarks and reduces profit and loss.
New findings challenge the importance of forecast accuracy in battery storage optimization, highlighting the role of rank correlation instead.
problem The challenge of optimizing battery storage dispatch decisions in multi-market electricity trading using forecast accuracy metrics.
method A hierarchical three-layer optimization system trading in multiple markets (FCR, aFRR, day-ahead, intraday) with real market data.
result Rank correlation (Kendall tau) is a better predictor of intraday dispatch value than forecast accuracy (MAE), with a threshold of tau around 0.85-0.95 capturing up to 97-100% of perfect-foresight revenue.
Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing policies which generalize across tasks, despite training for thousands of hours equivalent real robot time. To address this shortcoming, we…
New approach treats coordination as an architectural layer to improve LLM-based multi-agent systems.
problem Coordination defects lead to high failure rates in LLM-based multi-agent systems.
method Treats coordination as a configurable architectural layer separable from agent logic and information access.
result Configurations leave distinguishable signatures, enabling architectural reasoning and Pareto frontiers.