arXiv research

FinGPT is an open-source financial LLM for democratizing financial data.

FinGPT democratizes financial data for LLMs, enabling innovation.

Special p-forms are forms which have components φ_{μ_1...μ_p} equal to +1,-1 or 0 in some orthonormal basis. A p-form φ\in Λ^p R^d is called democratic if the set of nonzero components {φ_{μ_1...μ_p}} is symmetric under the transitive action of a subgroup of O(d,Z) on the indices {1,...,d}. Knowledge of these symmetry …

LLMs help less-resourced researchers access costly data.

Framework simplifies AI access for all.

New approach for large-scale distributed learning systems that improve generalization performance.

The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratization cannot be achieved without greatly simplifying the process of collecting groundtruth for training and testing these systems. This grou…

The paper examines how algorithmic classification affects behavior and proposes democratizing stakes to mitigate predatory practices.

Ludwig simplifies deep learning for non-experts.

LLM4Causal democratizes causal reasoning via fine-tuned LLMs.

Paper proposes a new AI design philosophy for distributed learning.

The hyperbolic structure of equilateral pentagons is mapped to a tiling of the hyperbolic plane.

Proposes a transfer learning framework to improve U.S. election prediction models.

Paper proposes forecast-necessity testing for accurate causal interpretation in nonlinear time-series models.

Anti-ELAB protests affected Hong Kong firms' stock prices, especially those linked to pan-democrats.

FinRobot opens-source AI for financial tasks, breaking down complex problems.

AI could democratize education but risks inequality.

Scikit-multiflow is a multi-output/multi-label and stream data mining framework for the Python programming language. Conceived to serve as a platform to encourage democratization of stream learning research, it provides multiple state of the art methods for stream learning, stream generators and evaluators. scikit-mult…

New method reveals true causal functions in nonlinear time series, not just scores.

A new CNN approach for time series forecasting outperforms traditional RNNs.

We explain the meaning of local symmetries in physics.

Conversion of raw data into insights and knowledge requires substantial amounts of effort from data scientists. Despite breathtaking advances in Machine Learning (ML) and Artificial Intelligence (AI), data scientists still spend the majority of their effort in understanding and then preparing the raw data for ML/AI. Th…

Reincarnating RL reuses prior work to accelerate RL progress.

Study shows how high-budget agents can manipulate prediction markets.

Research designs first model for Amharic handwritten character recognition.

Using the new data from the OECD-WTO world network of economic activities we construct the Google matrix $G$ of this directed network and perform its detailed analysis. The network contains 58 countries and 37 activity sectors for years 1995 and 2008. The construction of $G$, based on Markov chain transitions, treats a…

Financial system being the place of metting capital flows (equality between saving and investment), a volatility of capital flows can destroy the robustness and good working of financial system, it means subvert financial stability. The same a weak financial system, few regulated and bad manage can exacerbate volatilit…

Single neural network predicts ImageNet model parameters for faster training.

Efficient search methods can outperform random search on challenging tasks.

HotNAS reduces AI search time from hundreds of GPU hours to less than 3 GPU hours.

Developing active inference agents for edge devices with limited resources.

New method for epidemic model inference using multinomial approximations.

Object detection is a computer vision field that has applications in several contexts ranging from biomedicine and agriculture to security. In the last years, several deep learning techniques have greatly improved object detection models. Among those techniques, we can highlight the YOLO approach, that allows the const…

WSB community outperforms investment banks in stock picks.

Big data repositories from online learning platforms such as Massive Open Online Courses (MOOCs) represent an unprecedented opportunity to advance research on education at scale and impact a global population of learners. To date, such research has been hindered by poor reproducibility and a lack of replication, largel…

While the Machine Learning (ML) landscape is evolving rapidly, there has been a relative lag in the development of the "learning systems" needed to enable broad adoption. Furthermore, few such systems are designed to support the specialized requirements of scientific ML. Here we present the Data and Learning Hub for sc…

General equilibrium equations in economics play the same role with many-body Newtonian equations in physics. Accordingly, each solution of the general equilibrium equations can be regarded as a possible microstate of the economic system. Since Arrow's Impossibility Theorem and Rawls' principle of social fairness will p…

A scalable system detects price anomalies in online marketplaces to improve customer experience.

TBIP uses texts to quantify lawmakers' political positions.

Single model learns physics from diverse data.

Non-experts have long made important contributions to machine learning (ML) by contributing training data, and recent work has shown that non-experts can also help with feature engineering by suggesting novel predictive features. However, non-experts have only contributed features to prediction tasks already posed by e…

A new cost-frugal HPO method controls training cost during optimization.

Among the central tenets of globalization is free migration of labor. Although much has been written about its benefits, little is known about the limitations of globalization, including how immigration affects the anti-globalist sentiment. Analyzing polls data, we find that over the last three years in a group of EU c…

SmallML predicts customer churn for SMEs with small data, improving accuracy by 24.2 points.

In accordance with "Democracy's Effect on Development: More Questions than Answers", we seek to carry out a study in following the description in the 'Questions for Further Study.' To that end, we studied 33 countries in the Sub-Saharan Africa region, who all went through an election which should signal a "step-up" for…

During the Great Recession, Democrats in the United States argued that government spending could be utilized to "grease the wheels" of the economy in order to create wealth and to increase employment; Republicans, on the other hand, contended that government spending is wasteful and discouraged investment, thereby incr…

Creating efficient deep neural networks involves repetitive manual optimization of the topology and the hyperparameters. This human intervention significantly inhibits the process. Recent publications propose various Neural Architecture Search (NAS) algorithms that automate this work. We have applied a customized NAS a…

Sparse representations have proven their efficiency in solving a wide class of inverse problems encountered in signal and image processing. Conversely, enforcing the information to be spread uniformly over representation coefficients exhibits relevant properties in various applications such as digital communications. A…