Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, or even learns an optimizer, in order to minimize the expected loss when the training procedure is un…
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
48 results for “short-horizon optimization”
A new model for heterogeneous populations optimizes consumption and investment over short horizons.
problem Optimizing consumption and investment in economies with a heterogeneous population over short time periods.
method Continuous-time general equilibrium framework with Brownian flow on a type space, solving vanishing-horizon problems under relative-income criteria.
result Existence and characterization of short-horizon Duesenberry equilibrium, with sharp asset-pricing implications.
Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.
problem Optimizing behavior for long-term goals in reinforcement learning with unstable long planning horizons.
method Reward tweaking learns a surrogate reward function that induces optimal behavior for the original task.
result Reward tweaking guides agents towards better long-term returns while planning for short horizons.
The paper explores MAB strategies for very short horizons, introducing new methods and showing improved performance.
problem Short horizon multi-armed bandit problems in games.
method Regression oracles, forced exploration, UCBT strategy.
result Combination of epsilon-greedy or epsilon-decreasing with regression oracles outperforms other strategies.
Filters on order flow improve short-term market directionality.
problem Improving directional signals from order flow in financial markets.
method Structural filters on order lifetime, modification count, and timing applied to BankNifty index futures.
result Filters on parent orders of executed trades show stronger directional association with returns.
Paper uses SciPhyRL for optimizing large institutional portfolios.
problem Optimizing large institutional portfolios with cumulative costs and practical short horizons.
method Formulates a continuous-time optimization problem, reduces it to solving an HJB equation, and uses PINN for direct solution.
result Learned Gibbs policy yields substantial out-of-sample Sharpe ratio improvements.
Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?cs.LG
Long horizon reinforcement learning is as hard as short horizon learning.
problem Understanding the difficulty of long horizon reinforcement learning problems.
method Introduced new concepts: ε-net for optimal policies and Online Trajectory Synthesis algorithm.
result Proved that sample complexity scales logarithmically with the planning horizon, refuting the conjecture.
The study reveals distinct patterns in retail investors' holding periods affecting stock returns.
problem Understanding the impact of retail investors' investment horizons on stock returns.
method Using self-reported holding periods from StockTwits, the study categorizes retail investors into long-horizon and short-horizon groups and analyzes their return patterns.
result Long-horizon retail investors exhibit underreaction to earnings announcements, while short-horizon investors show overreaction.
Short-term incentives lead to riskier trading strategies.
problem Optimal execution with performance barriers.
method Analyzes the impact of short-term performance incentives on trading behavior.
result Short-term incentives result in more aggressive but less risky trading strategies in the short term, but poorer performance over long periods.
Inverse statistics in economics is considered. We argue that the natural candidate for such statistics is the investment horizons distribution. This distribution of waiting times needed to achieve a predefined level of return is obtained from (often detrended) historic asset prices. Such a distribution typically goes t…
A Blessing in Disguise? DeFi Exploits and Short-Horizon Responses in U.S. Commercial Paper Spreadsq-fin.GN
DeFi exploits lead to reduced CP spreads, contrary to contagion hypothesis.
problem Vulnerabilities in DeFi destabilize traditional short-term funding markets.
method Analysis of commercial paper spreads and regulatory segmentation.
result DeFi exploits lead to a 'Flight-to-Quality' pattern, narrowing rather than widening CP spreads.
Solves VaR-constrained portfolio optimization in markets with stochastic volatility.
problem Optimizing portfolio in markets with stochastic volatility under VaR constraints.
method Dynamic programming approach to Heston's stochastic volatility model.
result Optimal investment strategy linked to unconstrained problem via a vega-neutral derivative.
This paper develops a method to select a reference contract for multi-contract quoting to minimize execution risk.
problem Minimizing execution risk in multi-contract quoting sequences.
method Develops a diagnostic framework using order-flow Hawkes forecasts and CLF to select a stable reference contract.
result Event-history and LOB-state signals offer complementary views for reference-contract selection.
We provide complete source code for building a fundamental industry classification based on publically available and freely downloadable data. We compare various fundamental industry classifications by running a horserace of short-horizon trading signals (alphas) utilizing open source heterotic risk models (https://ssr…
Optimal Investment Horizons for Stocks and Marketsphysics.soc-ph
The inverse statistics is the distribution of waiting times needed to achieve a predefined level of return obtained from (detrended) historic asset prices \cite{optihori,gainloss}. Such a distribution typically goes through a maximum at a time coined the {\em optimal investment horizon}, , which defines the most…
Hybrid ML ensemble predicts market risk and generates alpha.
problem Forecasting short-horizon market risk and generating alpha.
method Neural networks and tree-based voting models integrated for trading signal.
result Sharpe ratio of 2.51 and annualized CAPM alpha of +0.28.
Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.
problem Improving deep learning models for forecasting fat-tailed financial returns.
method Comparison of backbone architectures and output heads (point, Gaussian, Gaussian mixture) on S&P 500 monthly log-returns.
result Switching from point to Gaussian heads improves CRPS by about 1.3 percent, and from Gaussian to mixture adds another 2.4 percent.
Generically learns movement control policies from exploration data.
problem Movement optimization in physically based characters.
method Parameterizes actions as target states, learns low-level control policy.
result Improves movement optimization across multiple tasks and algorithms.
New algorithms for constrained online optimization with memory and predictions.
problem Control of constrained dynamical systems and scheduling with reconfiguration budgets.
method Proposed algorithms achieving sublinear regret and constraint violation under time-varying constraints, both with and without predictions.
result First algorithms achieving sublinear regret and constraint violation in constrained online optimization with memory.
We propose a 4-factor model for overnight returns and give explicit definitions of our 4 factors. Long horizon fundamental factors such as value and growth lack predictive power for overnight (or similar short horizon) returns and are not included. All 4 factors are constructed based on intraday price and volume data a…
We give a complete algorithm and source code for constructing general multifactor risk models (for equities) via any combination of style factors, principal components (betas) and/or industry factors. For short horizons we employ the Russian-doll risk model construction to obtain a nonsingular factor covariance matrix.…
Bayesian approach to portfolio selection reduces pessimism in frequent trading.
problem Tackling the challenge of estimating drift in Merton's portfolio selection model.
method Bayesian distributionally robust control with nonlinear Wasserstein projections.
result Reduced pessimism and improved performance in frequent rebalancing compared to existing methods.
Study shows priority access in ELA auctions is less valuable due to volatility risks.
problem Impact of volatility on time-based transaction ordering policies.
method Single-round model with risk-averse bidders, tested using ETH price data.
result Priority access is discounted due to volatility and risk aversion.
Russian-Doll Risk Modelsq-fin.PM
We give a simple explicit algorithm for building multi-factor risk models. It dramatically reduces the number of or altogether eliminates the risk factors for which the factor covariance matrix needs to be computed. This is achieved via a nested "Russian-doll" embedding: the factor covariance matrix itself is modeled v…
New framework for choosing optimal proxy metrics from past experiments.
problem Difficult to measure long-term treatment effects in experiments.
method Statistical framework to define and construct optimal proxy metrics.
result Optimal proxy metric depends on experiment's sample size.
Realized moments of higher order computed from intraday returns are introduced in recent years. The literature indicates that realized skewness is an important factor in explaining future asset returns. However, the literature mainly focuses on the whole market and on the monthly or weekly scale. In this paper, we cond…
Bayesian machine learning methods improve nowcasting with mixed frequency data.
problem Handling frequency mismatches and predicting short-term economic indicators.
method Developed Gaussian process (GP) methods for MIDAS regressions.
result Gaussian process-MIDAS methods offer gains in predictive accuracy.
Inverse Statistics for Stocks and Marketsphysics.soc-ph
In recent publications, the authors have considered inverse statistics of the Dow Jones Industrial Averaged (DJIA) [1-3]. Specifically, we argued that the natural candidate for such statistics is the investment horizons distribution. This is the distribution of waiting times needed to achieve a predefined level of retu…
Generative AI improves stock selection by synthesizing features from diverse data sources.
problem Automating feature discovery in stock market data.
method Used large language models with retrieval-augmented generation and structured prompting to synthesize features from various data sources.
result AI-generated features consistently outperform baselines, with Sharpe improvements ranging from 14% to 91%.
State-of-the-art forecasting methods using Recurrent Neural Net- works (RNN) based on Long-Short Term Memory (LSTM) cells have shown exceptional performance targeting short-horizon forecasts, e.g given a set of predictor features, forecast a target value for the next few time steps in the future. However, in many appli…
A new method for risk-averse decision-making in Markov processes with improved regret bounds.
problem Risk-averse decision-making in Markov processes.
method Introduces mini-batch measures and multipattern risk-averse problems in a feature-based -learning method.
result Proves a high-probability regret bound of for the -learning method.
The operational space of an autonomous vehicle (AV) can be diverse and vary significantly. This may lead to a scenario that was not postulated in the design phase. Due to this, formulating a rule based decision maker for selecting maneuvers may not be ideal. Similarly, it may not be effective to design an a-priori cost…
Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Modelscs.LG
MoE-F combines LLMs online for better time-series prediction.
problem Combining multiple LLMs for online time-series prediction.
method Time-adaptive stochastic filtering techniques to combine experts.
result MoE-F achieves 17% absolute and 48.5% relative F1 measure improvement.
Financial event studies often misestimate causal effects due to misspecified factor models.
problem Misspecification of factor models in financial event studies leads to inconsistent estimates of causal effects.
method Proposed synthetic control methods to construct replicating portfolios from control securities.
result Synthetic control methods provide more accurate estimates of causal effects in event studies.
Project forecasts liquidity withdrawal using machine learning models.
problem Predicting liquidity withdrawal at individual stock levels.
method Tested a framework using machine learning models (AR, HAR, XGBoost) on Nasdaq MBO data.
result Introduced the Liquidity Withdrawal Index (LWI) for measuring liquidity removal.
Deep Learning for Short Term Equity Trend Forecasting: A Behavior Driven Multi Factor Approachq-fin.TR
Study uses deep learning to predict stock trends with superior performance.
problem Predicting short-term equity trends with high accuracy.
method Dual-task multilayer perceptron (MLP) integrating technical signals and deep learning.
result Deep learning model outperforms linear baselines in multi-factor stock selection.
Bayesian model predicts interest rates with short-term accuracy and long-term stability.
problem Improving short- and long-term prediction of time series with temporary non-stationary behavior.
method Time-varying autoregressive model with Bayesian regularization and MCMC inference.
result Model outperforms existing methods in both short and long-term predictions.
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors. The classic challenges in the information acquisition prob…
The paper develops a new model-free formula for option initial margins.
problem Calculating initial margins for option portfolios is complex and risky.
method The authors derive a new approximation formula for VaR without assuming a model.
result The new formula performs better than existing methods in simulations.
Algometrics analyzes how predictive models affect their own forecasts in algorithmic markets.
problem How predictive models affect their own forecasts in algorithmic markets.
method Introduces algometrics, a framework for time series with feedback, proving three results on deployment risk.
result Deployment risk cannot be identified from passive historical data alone, and historical rankings can invert under crowding.
New algorithm offers costless model selection in contextual bandits.
problem Minimizing cumulative regret in stochastic contextual bandits.
method Gradually increasing class complexity and adapting to the simplest class with dominant estimation variance.
result Costless model selection is feasible under certain conditions, providing improved regret guarantees.
Study causal financial signals for non-stationary markets, improving short-term forecasts.
problem Short-term forecasting in non-stationary financial markets under causal constraints.
method Construct causal signals from heterogeneous micro-features using causal centering, linear aggregation, Kalman filter, and forward-like operator.
result Causally constructed observables can exhibit substantial economic relevance in specific regimes but degrade under regime shifts.
Cryptocurrency patterns stable across market caps, validated by microstructure theory.
problem Stable patterns in cryptocurrency microstructure across different market caps.
method Unified CatBoost modeling pipeline with time-series cross validation, validated by backtests.
result Feature rankings and partial effects are stable across assets despite heterogeneous liquidity and volatility.
Simple models outperformed sophisticated ones in forecasting Turkish lira exchange rates.
problem Forecasting Turkish lira exchange rates through univariate techniques.
method Used several models including simple exponential smoothing to predict daily exchange rates.
result Simple exponential smoothing model outperformed all other alternatives.
Study finds anomalies in high-frequency S&P 500 price changes.
problem Anomalies in high-frequency S&P 500 price changes.
method Using NBBO event-time data, the study forms pairs of backward and forward price increments, standardizes them, and estimates expected responses on a fine grid of push magnitudes.
result Persistent structural shift in expected responses: near zero for short lags, pronounced tails for long lags, indicating correlation between larger historical pushes and nonzero responses.
Spectral portfolio theory links neural networks to wealth dynamics via SGD weight matrices.
problem Understanding wealth dynamics from neural network training.
method Direct identification of weight matrices as portfolio allocation matrices, linking SGD forces to portfolio dynamics.
result Spectral properties of SGD weight matrices transition between additive and multiplicative regimes, influencing wealth dynamics.
Proposes a new framework for invariant quadratic P&L predictions in option books.
problem Inconsistent second-order P&L predictions across different factor parameterizations.
method Local, model-agnostic framework using covariant Hessian defined by an affine connection.
result Coordinate-invariant quadratic P&L predictions that match desk targets.
Unified Latent Dynamics unifies model-free and model-based reinforcement learning.
problem Combining the efficiency of model-free methods with the representational strengths of model-based approaches.
method Embedding state-action pairs into a latent space where the true value function is approximately linear, using synchronized updates of encoder, value, and policy networks.
result ULD achieves cross-domain competence with minimal tuning and a fraction of the parameter footprint.