Climate policy debate is complex due to various interests.
problem Complex climate policy debate due to multiple interests.
method Analyzes motivations of different groups involved in climate debate.
result Climate policy will become simpler as Paris Agreement shifts focus to national governments.
Economics debated as a natural science.
problem Whether Economics should be considered a natural science.
method Discussion of the debate in a special issue of Euro. Phys. J. Special Topic.
result Economics remains a social science, not a natural science.
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.
AI systems learn complex goals via debate with human judges.
problem Complex human goals and preferences for AI systems.
method Training agents via self-play on a debate game, where humans judge which agent gives more true, useful information.
result Boosted classifier accuracy from 48.2% to 85.2% given 4 pixels, and from 59.4% to 88.9% given 6 pixels.
Method tracks conversational flow in debates.
problem Understanding how ideas flow in debates.
method Tracking interactive component of debates.
result Winners use interactive component better than losers.
The UN General Debate Corpus analyzes speeches from UN member states to reveal their political positions.
problem Lack of data on state preferences in international politics.
method Text analysis of over 7,700 speeches from 1970-2016.
result Demonstrates how the UN General Debate Corpus can reveal country positions on various policy dimensions.
A novel fact-checking method using debate dynamics on knowledge graphs.
problem Fact-checking on knowledge graphs with user comprehension and interactive reasoning.
method Reinforcement learning agents debate on paths in the graph to classify facts as true or false.
result Interactive reasoning and user understanding of AI decisions on knowledge graphs.
Advocates for Marr's levels of analysis to unify machine learning debates.
problem Challenges in aligning perspectives among machine learning researchers.
method Introduces Marr's levels of analysis from cognitive science and neuroscience.
result Marr's levels facilitate understanding and dissection of machine learning methods.
A method for reasoning on knowledge graphs using debate dynamics.
problem Automatic reasoning on knowledge graphs with interpretability.
method Reinforcement learning agents debate over facts, judge decides truth.
result Method outperforms baselines on triple classification and link prediction tasks.
Granger causality reviewed and advanced for complex data.
problem Validity of inferring causal relationships from time series data.
method Recent advances in models for high-dimensional time series, accounting for nonlinear and non-Gaussian observations, and sub-sampled data.
result Improved computational tools for Granger causality.
Paper proposes using word embeddings to detect trolls in social media debates.
problem Preventing online harassment through rapid detection of offensive posts.
method Word embedding models for identifying fast-changing topics and negative content.
result GloVe model helps in discovering new keywords for trolling detection.
Simplified LSTM models improve sentiment analysis on Twitter debate data.
problem Performing sentiment analysis on long sequence data from Twitter debates.
method Developed six parameter-reduced LSTM models (slim LSTM) for faster training and reduced computational cost.
result Slim LSTM models outperform standard LSTM model in sentiment analysis of GOP Debate Twitter dataset.
Article calls for data scientists to join ethics debate.
problem Impact of data science on society and ethics.
method Systematic approach from CNIL, established ethical guidelines.
result Data science requires professional ethics to build trust.
Crowd opinions in microblogs can predict event outcomes, matching with expert opinions.
problem Utilizing crowd wisdom for event outcome prediction in microblogs.
method Multi-label sentiment classification of tweets to gauge crowd opinion and compare with expert predictions.
result Crowd opinions in microblogs often match with expert opinions, especially in non-debate events.
Paper uses neural word embeddings to analyze UN speeches for policy preferences and voting behavior.
problem Analyzing policy preferences and paradigm shifts in international politics.
method Applied neural word embeddings (Word2vec) to UN General Debate speeches.
result Found statistical relation between speech semantic content and voting behavior, contrary to hypothesis.
Study uses few-shot learning to analyze claims and arguments in German debate on arms deliveries.
problem Limited data and computational resources for automated content analysis.
method Multilingual transformer model with adapter extension and few-shot learning.
result Parameter-efficient approach performs well on varying training set sizes.
This study models FOMC policy decisions using debate-based LLMs.
problem Accurately predicting central bank policy decisions, especially FOMC's, is challenging.
method A novel framework that simulates FOMC's collective decision-making process through iterative rounds of LLMs interacting as agents.
result The debate-based approach significantly outperforms standard LLMs in prediction accuracy.
New approach detects racial segregation patterns in machine learning systems.
problem Challenges of fairness in machine learning systems due to racial identity.
method Unsupervised learning to detect patterns of segregation.
result Mitigates root cause of social disparities without reifying race.
ICT intensification impacts employment across sectors in India.
problem Impact of ICT on employment in Indian sectors.
method Analysis of ICT investment intensity across sectors.
result ICT intensification correlates with employment changes across sectors.
New theory of co~events resolves debates between Bayesianists and frequentists.
problem Fierce debates between Bayesianists and frequentists over Bayesian scheme.
method Developed new co~event axiomatics and theory to study experience and chance as a single co~event.
result Demonstrated effectiveness of new theory in resolving debates over Bayesian scheme.
Graphical interpretation of unfairness in causal Bayesian networks.
problem Unfairness in datasets and models.
method Causal Bayesian networks to interpret and measure unfairness.
result Causal Bayesian networks provide a tool to measure and design fair models.
Paper explores broader bias issues in ML systems beyond training data.
problem Technical and emergent biases in automated decision-making systems.
method Interprets technical bias as epistemological and emergent bias as dynamical.
result Need to reflect on epistemology and use value-sensitive design.
Paper resolves the debate on process vs. outcome supervision in reinforcement learning.
problem Distinguishing between process and outcome supervision in reinforcement learning.
method Developed a technical tool (Change of Trajectory Measure Lemma) to show equivalence between outcome and process supervision under standard data coverage assumptions.
result Reinforcement learning through outcome supervision is statistically equivalent to process supervision, up to polynomial factors in horizon.
Investment strategy depends on many factors for venture capital funds.
problem Finding the optimal portfolio size for venture capital funds.
method Analyzes various factors affecting fund returns and optimal portfolio size, starting with basic assumptions and increasing complexity.
result Investment strategy depends on many factors, not a one-size-fits-all formula.
This work addresses fairness constraints for multiple subpopulations in machine learning models.
problem Fairness constraints for multiple subpopulations in machine learning models.
method Constraining the expected outcome of subpopulations in kernel regression and decision tree regression, specifically random forests and boosted trees.
result The proposed solution does not affect the computational or memory complexity of decision trees and can be easily integrated post training.
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
Potential Future Exposure (PFE) is a standard risk metric for managing business unit counterparty credit risk but there is debate on how it should be calculated. The debate has been whether to use one of many historical ("physical") measures (one per calibration setup), or one of many risk-neutral measures (one per num…
This expository paper is a tribute to Ekkehart Kröner's results on the intrinsic non-Riemannian geometrical nature of a single crystal filled with point and/or line defects. A new perspective on this old theory is proposed, intended to contribute to the debate around the still open Kröner's question: "what are the dyna…
Crowdsourced investigation shows differing results for technical analysis strategies.
problem Differing results in technical analysis strategies due to lack of method.
method Collaborative scientific computational framework using Monte Carlo simulations and historical back testing.
result Results are not repeatable by other researchers, highlighting the need for transparency and robustness.
MakerDAO's governance is centralized despite its decentralized claim.
problem Decentralization illusion in Decentralized Finance (DeFi) governance.
method Empirical analysis using financial, transaction, network, and sentiment indicators.
result Centralized governance impacts Maker protocol and voting power distribution.
With a point of departure in the concept "uncomfortable knowledge," this article presents a case study of how the American Planning Association (APA) deals with such knowledge. APA was found to actively suppress publicity of malpractice concerns and bad planning in order to sustain a boosterish image of planning. In th…
D-ETM models document topics over time using embeddings and variational inference.
problem Capturing evolving topic patterns in sequential documents.
method Combines D-LDA and word embeddings, using random walk priors and variational inference.
result D-ETM outperforms D-LDA on document completion tasks, learning more diverse and coherent topics.
New framework models uncertainty in classification debates.
problem Weak interpretability of existing uncertainty quantification methods.
method Courtroom analogy and Mixture of Dirichlet Experts (MoDEX) model.
result MoDEX achieves state-of-the-art uncertainty quantification performance.
This paper reviews bank performance determinants, highlighting future research areas.
problem Understanding bank performance factors to improve sector efficiency and knowledge.
method Analysis of 54 studies in peer-reviewed journals.
result Bank performance factors remain largely unexplored, especially post-COVID-19.
Proves lower discount rates are needed for future losses.
problem Determining appropriate discount rates for future losses.
method Analyzes climate change and discount rates debate.
result Risk requires a lower, not higher, discount rate.
Topological parallax assesses AI models' geometric similarity to datasets for safety.
problem Ensuring AI models' robustness and safety in deep learning applications.
method Topological parallax compares a trained model to a reference dataset using Rips complexes and geodesic distortions.
result Topological parallax indicates whether a model shares similar multiscale geometric features with the dataset.
The paper analyzes tech specialization and diversification at various scales.
problem Trade-offs between specialization and diversification in economic development.
method Patent data and Economic Complexity framework.
result Technological Coherence positively impacts growth at metropolitan areas but negatively at larger scales.
The Information Plane theory predicts autoencoders do not compress input information.
problem Understanding the training dynamics of hidden layers in autoencoders.
method Derive a theoretical convergence for the Information Plane of autoencoders using a Gram-matrix based mutual information estimator.
result Ideal autoencoders with a large bottleneck layer size do not compress input information, while a small size causes compression only in the encoder layers.
In the current environment of financial distress, many governments are likely to soon become major holders of financial assets, but the policy debate focuses only on the likelihood and extent of short-term market stabilization. This paper shows that government intervention and propping up are likely to lead to long-ter…
Explains why large neural nets generalize well and the role of regularization.
problem Understanding why large neural networks generalize well and the role of regularization.
method Numerical experiments and theoretical concepts discussion.
result Need for new theoretical concepts to explain neural network generalization.
The management of operational risk in the banking industry has undergone significant changes over the last decade due to substantial changes in operational risk environment. Globalization, deregulation, the use of complex financial products and changes in information technology have resulted in exposure to new risks ve…
Bayesian neural networks integrate uncertainty into neural networks for improved performance.
problem Overconfidence, lack of interpretability, and adversarial attacks in neural networks.
method Integrates Bayesian inference into neural networks to address limitations.
result BNNs improve model performance and provide uncertainty estimates.
Recent advances in the understanding of time series permit to clarify seasonalities and cycles, which might be rather obscure in today's literature. A theorem due to P. Cartier and Y. Perrin, which was published only recently, in 1995, and several time scales yield, perhaps for the first time, a clear-cut definition of…
New method learns complex brain signal patterns from EEG/MEG data.
problem Complex waveforms in brain signals not captured by linear filters.
method Multivariate convolutional sparse coding (CSC) algorithm.
result Reveals non-sinusoidal mu-shaped patterns in brain signals.
This work investigates how multi-round reasoning improves LLM performance.
problem Improving problem-solving abilities in complex tasks with LLMs.
method Investigates approximation, learnability, and generalization properties of multi-round auto-regressive models.
result Transformers with finite context windows are universal approximators for Turing-computable functions and can approximate any Turing-computable sequence-to-sequence function through multi-round reasoning.
The use of the trading halts is a practice common to all markets. However, the advantages and the disadvantages of the measurements are regularly discussed. The partisans think that the trading suspensions or the price limits make it possible to the investors to have time to react to the new information. The detractors…
Study quantifies reproducibility of machine learning papers.
problem Lack of empirical reproducibility metrics in machine learning.
method Manual implementation of 255 papers from 1984-2017, analyzing features and results.
result Manual implementation revealed discrepancies between papers and their descriptions.
Geospatial ML models need special evaluation methods due to their unique challenges.
problem Evaluating geospatial machine learning models is challenging due to their specific characteristics.
method Delineated unique challenges and proposed concrete takeaways for improving geospatial model evaluations.
result Concrete takeaways for improving evaluations of geospatial model performance.