금융 지수 추적을 위한 강화 학습: 거래 비용을 고려한 동적 접근 방식
본 논문에서는 거래 비용을 고려하여 장기간에 걸쳐 지수 추적 오류와 거래 비용 간의 균형을 맞추는 동적 지수 추적 전략을 제시하고, 이를 강화 학습을 통해 해결하는 방법을 제안합니다.
金融インデックストラッキングのための強化学習：動的な定式化と実証分析
本稿では、従来の静的な定式化が抱える問題を克服するため、取引コストを考慮した動的なインデックストラッキング問題の定式化を提案し、その問題に対する深層強化学習ベースの新しい解決策を提示する。
Analyzing Visual Token Redundancy in Multi-modal Large Language Models for Efficient Training and Inference
Multi-modal Large Language Models (MLLMs) exhibit significant redundancy in their processing of visual information, and this redundancy can be leveraged to develop more efficient training and inference methods without significantly impacting performance.
逐次較正における $T^{2/3}$ の壁を打ち破る
本論文では、逐次較正問題において、従来の較正誤差の上限であるO(T 2/3)をO(T 2/3−ε)に改善する新しいアルゴリズムを提案し、符号保存ゲームとの双方向的な関係性を示すことで、較正誤差の下限を改善しました。
OCTree: Using LLMs and Decision Tree Reasoning for Automated Feature Generation in Tabular Data
OCTree is a novel framework that leverages large language models (LLMs) and decision tree reasoning to automate the generation of effective features for tabular data, improving the performance of various prediction models.
基於數據驅動的非線性波動力學模型重構
本文提出了一種基於機器學習的框架，用於分析複雜波介質中光波包的非線性演化動力學，並通過稀疏回歸將微觀離散晶格模型簡化為更簡單的有效連續介質模型，以準確描述波包的動態。
비선형 파동 역학을 위한 데이터 기반 모델 재구성: 광 도메인 벽에서의 비선형 효과 분석 및 효과적인 연속체 모델 도출
본 연구는 머신러닝을 사용하여 복잡한 파동 매질에서 광 도메인 벽에 국한된 비선형 광파 패킷의 역학을 정확하게 설명하는 간소화된 연속체 모델을 추출하는 방법을 제시합니다.
複雑な波動媒質における非線形波動ダイナミクスのデータ駆動型モデル再構成：解釈可能な機械学習アプローチ
本稿では、複雑な波動媒質における光波束の非線形進化ダイナミクスを解析するための、解釈可能な機械学習フレームワークを提示しています。具体的には、ハニカムフォトニック格子におけるバレーホールドメイン壁を対象に、スパース回帰を用いて微視的な離散格子モデルを、波束エンベロープのダイナミクスを正確に記述できる、より単純な有効連続体モデルに縮小します。
Data-Driven Machine Learning Reconstruction of Effective Continuum Models for Nonlinear Wave Dynamics in Photonic Lattices
Machine learning, specifically sparse regression, can be used to construct accurate and interpretable effective continuum models for complex nonlinear wave dynamics in photonic lattices, offering an alternative to traditional analytical methods.
HistoEncoder: A Foundation Model for Prostate Cancer Digital Pathology Outperforms ImageNet-based Models
A novel foundation model, HistoEncoder, trained on a vast dataset of prostate tissue images, demonstrates superior performance in prostate cancer detection and mortality prediction compared to models pre-trained on natural images, achieving high accuracy with significantly less data and computational resources.
© 2024 by Linnk AI