Diffusion Model-based Probabilistic Downscaling for 180-year East Asian...
As our planet is entering into the "global boiling" era, understanding regional climate change becomes imperative. Effective downscaling methods that provide localized insights are crucial for this...
View ArticleFrom GARCH to Neural Network for Volatility Forecast
Volatility, as a measure of uncertainty, plays a crucial role in numerous financial activities such as risk management. The Econometrics and Machine Learning communities have developed two distinct...
View ArticleTransformers with Attentive Federated Aggregation for Time Series Stock...
Recent innovations in transformers have shown their superior performance in natural language processing (NLP) and computer vision (CV). The ability to capture long-range dependencies and interactions...
View ArticleLarge (and Deep) Factor Models
We open up the black box behind Deep Learning for portfolio optimization and prove that a sufficiently wide and arbitrarily deep neural network (DNN) trained to maximize the Sharpe ratio of the...
View ArticleSocraSynth: Multi-LLM Reasoning with Conditional Statistics
Large language models (LLMs), while promising, face criticisms for biases, hallucinations, and a lack of reasoning capability. This paper introduces SocraSynth, a multi-LLM agent reasoning platform...
View ArticleMDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and...
The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such...
View ArticleFAST: Factorizable Attention for Speeding up Transformers
Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high...
View ArticlePolicy Improvement using Language Feedback Models
We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train...
View ArticleImplicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation...
In modern machine learning, models can often fit training data in numerous ways, some of which perform well on unseen (test) data, while others do not. Remarkably, in such cases gradient descent...
View ArticleScaling Laws for Fine-Grained Mixture of Experts
Mixture of Experts (MoE) models have emerged as a primary solution for reducing the computational cost of Large Language Models. In this work, we analyze their scaling properties, incorporating an...
View ArticleNesting Particle Filters for Experimental Design in Dynamical Systems
In this paper, we propose a novel approach to Bayesian Experimental Design (BED) for non-exchangeable data that formulates it as risk-sensitive policy optimization. We develop the Inside-Out SMC^2...
View ArticleMultiscale Neuroimaging Features for the Identification of Medication Class...
In the clinical treatment of mood disorders, the complex behavioral symptoms presented by patients and variability of patient response to particular medication classes can create difficulties in...
View ArticleComparing skill of historical rainfall data based monsoon rainfall prediction...
In this draft we consider the problem of forecasting rainfall across India during the four monsoon months, one day as well as three days in advance. We train neural networks using historical daily...
View ArticleGenerative Modeling of Discrete Joint Distributions by E-Geodesic Flow...
This paper introduces a novel generative model for discrete distributions based on continuous normalizing flows on the submanifold of factorizing discrete measures. Integration of the flow gradually...
View ArticleAn Investigation into Using Unsupervised Metrics to Optimise GNNs for Node...
Graph Neural Networks (GNNs) can be trained to detect communities within a graph by learning from the duality of feature and connectivity information. Currently, the common approach for optimisation of...
View ArticleGeneralizing across Temporal Domains with Koopman Operators
In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes...
View ArticleOn Computationally Efficient Multi-Class Calibration
Consider a multi-class labelling problem, where the labels can take values in $[k]$, and a predictor predicts a distribution over the labels. In this work, we study the following foundational question:...
View ArticleDifferentially Private Zeroth-Order Methods for Scalable Large Language Model...
Finetuning on task-specific datasets is a widely-embraced paradigm of harnessing the powerful capability of pretrained LLMs for various downstream tasks. Due to the popularity of LLMs finetuning and...
View ArticleSourcerer: Sample-based Maximum Entropy Source Distribution Estimation
Scientific modeling applications often require estimating a distribution of parameters consistent with a dataset of observations - an inference task also known as source distribution estimation. This...
View ArticleEmpowering Federated Learning for Massive Models with NVIDIA FLARE
In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine...
View Article