On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “prediction-guided”

Prediction-Guided Active Experimentsstat.ML

PGAE uses predictions to guide active experimentation.

problem Efficiently guiding experimental sampling based on predictions.

method PGAE framework that combines predictions and actual outcomes.

result PGAE achieves asymptotic optimality and efficiency.

active experimentation prediction-guided machine learning asymptotic optimality efficiency bound

2024-11-18abs ↗pdf ↗

BiHRNN -- Bi-Directional Hierarchical Recurrent Neural Network for Inflation Forecastingcs.LG

BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.

problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.

method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.

result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.

inflation forecasting BiHRNN recurrent neural networks hierarchical structure bidirectional flow

2025-02-27abs ↗pdf ↗

Outside the Echo Chamber: Optimizing the Performative Riskcs.LG

This paper optimizes performative risk by focusing on convex properties and developing efficient algorithms.

problem Performative risk, the loss experienced by decision makers, is not optimized by stable models.

method Identifying convex properties of loss function and model-induced distribution shift, developing algorithms for optimization.

result Optimization of performative risk with better sample efficiency than generic methods.

performative prediction performative risk convex optimization sample efficiency decision making

2021-02-17abs ↗pdf ↗

Exploring Sectoral Profitability in the Indian Stock Market Using Deep Learningq-fin.CP

Deep learning LSTM predicts stock prices for portfolio design in Indian sectors.

problem Predicting stock prices in Indian stock market.

method Long Short-Term Memory (LSTM) model for historical stock price prediction.

result Efficacy of LSTM model in predicting stock prices and informing investment decisions.

Deep Learning Stock Prediction Portfolio Design Indian Stock Market LSTM

2024-05-28abs ↗pdf ↗

Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scalingcs.LG

ePF improves PF for ITS by balancing exploration and exploitation, outperforming baselines.

problem Premature exploitation in PF leads to suboptimal solutions under constrained budgets.

method Integrates Entropic Annealing and Look-ahead Modulation to preserve diversity and evaluate potential.

result Significant improvement in task reward (up to 50% relative) on math benchmarks.

Particle Filtering Monte Carlo Inference-Time Scaling Premature Exploitation Entropy

2025-10-07abs ↗pdf ↗