Related papers: Market-Driven Subset Selection for Budgeted Traini…

Collecting annotated data for semantic segmentation is time-consuming and hard to scale up. In this paper, we for the first time propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented…

Data analytics using machine learning (ML) has become ubiquitous in science, business intelligence, journalism and many other domains. While a lot of work focuses on reducing the training cost, inference runtime and storage cost of ML…

Adapting language models to new tasks through continued pretraining faces a fundamental trade-off: models must learn new capabilities while avoiding catastrophic forgetting of existing knowledge. While prior work has studied synthetic data…

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

When solving decision and optimisation problems, many competing algorithms (model and solver choices) have complementary strengths. Typically, there is no single algorithm that works well for all instances of a problem. Automated algorithm…

This paper explores neural network-based approaches for algorithmic trading in cryptocurrency markets. Our approach combines multi-timeframe trend analysis with high-frequency direction prediction networks, achieving positive risk-adjusted…

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly…

Data selection can reduce the amount of training data needed to finetune LLMs; however, the efficacy of data selection scales directly with its compute. Motivated by the practical challenge of compute-constrained finetuning, we consider the…

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

The optimal solution to an optimization problem depends on the problem's objective function, constraints, and size. While deep neural networks (DNNs) have proven effective in solving optimization problems, changes in the problem's size,…

This paper investigates the integration of large language models (LLMs) as reasoning agents in repeated spectrum auctions within heterogeneous networks (HetNets). While auction-based mechanisms have been widely employed for efficient…

Data collection is a critical component of modern statistical and machine learning pipelines, particularly when data must be gathered from multiple heterogeneous sources to study a target population of interest. In many use cases, such as…

We consider the problem of dynamic buying and selling of shares from a collection of $N$ stocks with random price fluctuations. To limit investment risk, we place an upper bound on the total number of shares kept at any time. Assuming that…

A diverse array of reasoning strategies has been proposed to elicit the capabilities of large language models. However, in this paper, we point out that traditional evaluations which focus solely on performance metrics miss a key factor:…

The decisions traders make to buy or sell an asset depend on various analyses, with expertise required to identify patterns that can be exploited for profit. In this paper we identify novel features extracted from emergent and…

We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Despite considerable progress in multi-task learning, most efforts focus on learning from multi-label data: a single image…

Hand-tagged training data is essential to many machine learning tasks. However, training data quality control has received little attention in the literature, despite data quality varying considerably with the tagging exercise. We propose…

This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories…