Search

Search

Papers, wiki, Option Blackboard, encyclopedia, and cards.

Results for “training” · papers 18 · wiki 17
Academic Papers · 18arXiv q-fin live 8 · desk corpus 41
arXiv · arXiv · 2026

Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting

Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memory and computational cost. Post-training quantization (PTQ) enables such deployment without retraining. However, reliable activation quantization requires calibration: activation ranges are estimated from historical data before deployment and then remain fixed during f

Junyi Ye, Ivy Gateri Wanjiku
arXiv · arXiv · 2026

From Index to Equity: Pre-Training Transformers for Stock Return Prediction

This research aims to leverage machine learning to improve stock price prediction and support informed investment decisions related to buying, selling, and holding assets. Specifically, this work investigates transformer-based models for stock prediction and examines the impact of pre-training strategies on forecasting performance. A transformer model was first pre-trained on the Toronto Stock Exchange Index (TSX) to

Marie Soehl Coolsaet, Roberto Gallardo, Zhen Gao
arXiv · arXiv · 2026

Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training

This paper proposes a machine learning assisted portfolio optimization framework designed for low data environments and regime uncertainty. We construct a teacher student learning pipeline in which a Conditional Value at Risk (CVaR) optimizer generates supervisory labels, and neural models (Bayesian and deterministic) are trained using both real and synthetically augmented data. The synthetic data is generated using

Adhiraj Chattopadhyay
arXiv · arXiv · 2026

Unlocking Noisy Real-World Corpora for Foundation Model Pre-Training via Quality-Aware Tokenization

Current tokenization methods process sequential data without accounting for signal quality, limiting their effectiveness on noisy real-world corpora. We present QA-Token (Quality-Aware Tokenization), which incorporates data reliability directly into vocabulary construction. We make three key contributions: (i) a bilevel optimization formulation that jointly optimizes vocabulary construction and downstream performance

Arvid E. Gollwitzer, Paridhi Latawa, David de Gruijl, Deepak A. Subramanian, Adrián Noriega de la Colina
arXiv · arXiv · 2024

The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging

This paper proposes a novel method for constructing instruction-tuned large language models (LLMs) for finance without instruction data. Traditionally, developing such domain-specific LLMs has been resource-intensive, requiring a large dataset and significant computational power for continual pretraining and instruction tuning. Our study proposes a simpler approach that combines domain-specific continual pretraining

Masanori Hirano, Kentaro Imajo
arXiv · arXiv · 2023

Co-Training Realized Volatility Prediction Model with Neural Distributional Transformation

This paper shows a novel machine learning model for realized volatility (RV) prediction using a normalizing flow, an invertible neural network. Since RV is known to be skewed and have a fat tail, previous methods transform RV into values that follow a latent distribution with an explicit shape and then apply a prediction model. However, knowing that shape is non-trivial, and the transformation result influences the p

Xin Du, Kai Moriyama, Kumiko Tanaka-Ishii
arXiv · arXiv · 2023

Non-adversarial training of Neural SDEs with signature kernel scores

Neural SDEs are continuous-time generative models for sequential data. State-of-the-art performance for irregular time series generation has been previously obtained by training these models adversarially as GANs. However, as typical for GAN architectures, training is notoriously unstable, often suffers from mode collapse, and requires specialised techniques such as weight clipping and gradient penalty to mitigate th

Zacharia Issa, Blanka Horvath, Maud Lemercier, Cristopher Salvi
arXiv · arXiv q-fin · 2019

Automatic Financial Trading Agent for Low-risk Portfolio Management using Deep Reinforcement Learning

The autonomous trading agent is one of the most actively studied areas of artificial intelligence to solve the capital market portfolio management problem. The two primary goals of the portfolio management problem are maximizing profit and restrainting risk. However, most approaches to this problem solely take account of maximizing returns. Therefore, this paper proposes a deep reinforcement learning based trading ag

Wonsup Shin, Seok-Jun Bu, Sung-Bae Cho
arXiv · arXiv q-fin · 2026

Market Informedness and Market-Maker Profitability: The Trade-Off Between Adverse Selection and Price Discovery

This paper studies how market informedness affects market makers' profitability in a computational market environment with heterogeneous learning agents. We develop an agent-based market model in which market makers differ in their information sets and inventory-risk aversion, prices form endogenously, fundamental values evolve exogenously, and market-taker order flow follows a state-dependent self-exciting process.

Konrad Ochędzan, Nino Antulov-Fantulin
arXiv · arXiv q-fin · 2025

Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy

Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-crit

Hongyang Yang, Xiao-Yang Liu, Shan Zhong, Anwar Walid
arXiv · arXiv q-fin · 2025

TRADES: Generating Realistic Market Simulations with Diffusion Models

Financial markets are complex systems characterized by high statistical noise, nonlinearity, volatility, and constant evolution. Thus, modeling them is extremely hard. Here, we address the task of generating realistic and responsive Limit Order Book (LOB) market simulations, which are fundamental for calibrating and testing trading strategies, performing market impact experiments, and generating synthetic market data

Leonardo Berti, Bardh Prenkaj, Paola Velardi
arXiv · arXiv q-fin · 2021

FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance

Deep reinforcement learning (DRL) has been envisioned to have a competitive edge in quantitative finance. However, there is a steep development curve for quantitative traders to obtain an agent that automatically positions to win in the market, namely \textit{to decide where to trade, at what price} and \textit{what quantity}, due to the error-prone programming and arduous debugging. In this paper, we present the fir

Xiao-Yang Liu, Hongyang Yang, Jiechao Gao, Christina Dan Wang
arXiv · arXiv q-fin · 2021

FinRL-Podracer: High Performance and Scalable Deep Reinforcement Learning for Quantitative Finance

Machine learning techniques are playing more and more important roles in finance market investment. However, finance quantitative modeling with conventional supervised learning approaches has a number of limitations. The development of deep reinforcement learning techniques is partially addressing these issues. Unfortunately, the steep learning curve and the difficulty in quick modeling and agile development are impe

Zechu Li, Xiao-Yang Liu, Jiahao Zheng, Zhaoran Wang, Anwar Walid
arXiv · arXiv · 2019

Systemic liquidity contagion in the European interbank market

Systemic liquidity risk, defined by the IMF as "the risk of simultaneous liquidity difficulties at multiple financial institutions", is a key topic in macroprudential policy and financial stress analysis. Specialized models to simulate funding liquidity risk and contagion are available but they require not only banks' bilateral exposures data but also balance sheet data with sufficient granularity, which are hardly a

V. Macchiati, G. Brandi, G. Cimini, G. Caldarelli, D. Paolotti
arXiv · arXiv · 2026

Regime-Adaptive Continual Learning for Portfolio Management

Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management (PM) approaches ineffective. Existing remedies, such as rolling-window retraining and naive online fine-tuning, are hindered by high computational costs and insufficient knowledge utilization, respectively, resulting in low returns and limited adaptability. Continual l

Chaofan Pan, Lingfei Ren, Linbo Xiong, Yonghao Li, Wei Wei
arXiv · arXiv · 2026

PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management

Large language models (LLMs) have shown strong performance across diverse financial tasks, yet portfolio management (PM) remains poorly benchmarked. Existing benchmarks exhibit two gaps: they are often equity-only and ignore cross-asset correlations; they fail to evaluate the complete PM decision pipeline. We introduce PortBench, a benchmark spanning six heterogeneous asset classes from 2015 to 2025. PortBench compri

Yuxuan Zhao, Sijia Chen, Ningxin Su
arXiv · arXiv · 2025

Supervised Similarity for High-Yield Corporate Bonds with Quantum Cognition Machine Learning

We investigate the application of quantum cognition machine learning (QCML), a novel paradigm for both supervised and unsupervised learning tasks rooted in the mathematical formalism of quantum theory, to distance metric learning in corporate bond markets. Compared to equities, corporate bonds are relatively illiquid and both trade and quote data in these securities are relatively sparse. Thus, a measure of distance/

Joshua Rosaler, Luca Candelori, Vahagn Kirakosyan, Kharen Musaelian, Ryan Samson
arXiv · arXiv · 2025

Improving DeFi Accessibility through Efficient Liquidity Provisioning with Deep Reinforcement Learning

This paper applies deep reinforcement learning (DRL) to optimize liquidity provisioning in Uniswap v3, a decentralized finance (DeFi) protocol implementing an automated market maker (AMM) model with concentrated liquidity. We model the liquidity provision task as a Markov Decision Process (MDP) and train an active liquidity provider (LP) agent using the Proximal Policy Optimization (PPO) algorithm. The agent dynamica

Haonan Xu, Alessio Brini
Wiki Entities · 17
AI Systems

Adam Optimizer

Adam is an adaptive first-order optimizer that keeps exponential moving averages of the gradient and its square, giving per-parameter step sizes.

AI Systems

Backpropagation

Backpropagation computes gradients of a scalar loss with respect to every weight by applying the chain rule backwards through the computational graph.

AI Systems

Batch Normalization

Batch normalization re-centers and re-scales layer inputs using mini-batch statistics, then learns a scale and shift, reducing internal covariate shift and allowing higher learning rates.

AI Systems

Contrastive Learning

Contrastive learning pulls representations of related pairs together and pushes unrelated pairs apart. It is the pretraining idea behind SimCLR, CLIP, and many embedding models.

AI Systems

Dropout

Dropout randomly zeroes hidden units during training so the net cannot rely on any single co-adaptation, then scales weights at test time (or uses inverted dropout).

AI Systems

Early Stopping

Early stopping treats training time as a capacity knob: halt when a validation metric stops improving so the model does not wander into overfit.

AI Systems

Fine-Tuning

Fine-tuning continues training a pretrained model on a narrower distribution so the same weights specialize — classification heads, instruction following, or a desk domain.

AI Systems

Gradient Descent

Gradient descent updates parameters against the gradient of a loss: θ ← θ − η ∇_θ L. Stochastic and mini-batch variants make the method tractable on large datasets.

AI Systems

Layer Normalization

Layer normalization standardizes activations across features for each example, not across the batch — the stabilizer that made Transformers trainable.

AI Systems

Overfitting

Overfitting is when a model fits training idiosyncrasies instead of the transferable regularity, so held-out or live error rises even as train loss falls.

AI Systems

Retrieval-Augmented Generation

RAG retrieves relevant documents first, then conditions a language model on that evidence so answers can be grounded, cited, and updated without retraining.

AI Systems

Scaling Laws

Scaling laws are empirical power laws relating language-model loss to parameter count, data, and compute, used to plan pretraining rather than guess.

AI Systems

Teacher Forcing

Teacher forcing trains a sequential decoder on the ground-truth previous token instead of its own prediction — fast and biased, which is why exposure bias exists.

AI Systems

Vanishing Gradient

Vanishing gradients are when backprop multiplies many |Jacobian| < 1 factors so early layers receive ~0 update — the reason plain deep RNNs and tanh stacks died.

AI Systems

Variational Autoencoder

A VAE is a probabilistic autoencoder: the encoder outputs a distribution q(z|x), the decoder p(x|z), and training maximizes an ELBO with a KL term that keeps the latent well-behaved.

AI Systems

Xavier Initialization

Xavier/Glorot initialization scales initial weights so variance is preserved through a layer — the default that made deep tanh/sigmoid nets trainable before BatchNorm.

Mathematics

Kullback–Leibler Divergence

KL divergence KL(P‖Q) = E_P[log dP/dQ] is the expected extra log-loss from using Q when the truth is P — the loss behind cross-entropy training and many variational methods.

Option Blackboard · 0
No Option Blackboard entries matched.
Encyclopedia · 9
AI Systems · Foundations

Contrastive Learning

Contrastive learning pulls representations of related pairs together and pushes unrelated pairs apart. It is the pretraining idea behind SimCLR, CLIP, and many embedding models.

AI Systems · Foundations

Dropout

Dropout randomly zeroes hidden units during training so the net cannot rely on any single co-adaptation, then scales weights at test time (or uses inverted dropout).

AI Systems · Foundations

Early Stopping

Early stopping treats training time as a capacity knob: halt when a validation metric stops improving so the model does not wander into overfit.

AI Systems · Foundations

Fine-Tuning

Fine-tuning continues training a pretrained model on a narrower distribution so the same weights specialize — classification heads, instruction following, or a desk domain.

Mathematics · Foundations

Kullback–Leibler Divergence

KL divergence KL(P‖Q) = E_P[log dP/dQ] is the expected extra log-loss from using Q when the truth is P — the loss behind cross-entropy training and many variational methods.

AI Systems · Foundations

Overfitting

Overfitting is when a model fits training idiosyncrasies instead of the transferable regularity, so held-out or live error rises even as train loss falls.

AI Systems · Foundations

Retrieval-Augmented Generation

RAG retrieves relevant documents first, then conditions a language model on that evidence so answers can be grounded, cited, and updated without retraining.

AI Systems · Foundations

Scaling Laws

Scaling laws are empirical power laws relating language-model loss to parameter count, data, and compute, used to plan pretraining rather than guess.

AI Systems · Foundations

Variational Autoencoder

A VAE is a probabilistic autoencoder: the encoder outputs a distribution q(z|x), the decoder p(x|z), and training maximizes an ELBO with a KL term that keeps the latent well-behaved.

Cards · 0
No cards matched.
← Back to Codex