A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History-Dependent Experts

• URL: http://arxiv.org/abs/2007.12732v1
• Date: Fri, 24 Jul 2020 18:46:28 GMT
• Title: A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History-Dependent Experts
• Authors: Nadejda Drenska, Robert V. Kohn
• Abstract summary: We like to call it the'stock prediction problem,' viewing the sequence as the price history of a stock that goes up or down one unit at each time step. In this problem, an investor has access to the predictions of two or more 'experts,' and strives to minimize her final-time regret. We consider the case when there are two history-dependent experts, whose predictions are determined by the d most recent stock moves.
• Score: 0.6091702876917281
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The prediction of a binary sequence is a classic example of online machine learning. We like to call it the 'stock prediction problem,' viewing the sequence as the price history of a stock that goes up or down one unit at each time step. In this problem, an investor has access to the predictions of two or more 'experts,' and strives to minimize her final-time regret with respect to the best-performing expert. Probability plays no role; rather, the market is assumed to be adversarial. We consider the case when there are two history-dependent experts, whose predictions are determined by the d most recent stock moves. Focusing on an appropriate continuum limit and using methods from optimal control, graph theory, and partial differential equations, we discuss strategies for the investor and the adversarial market, and we determine associated upper and lower bounds for the investor's final-time regret. When d is less than 4 our upper and lower bounds coalesce, so the proposed strategies are asymptotically optimal. Compared to other recent applications of partial differential equations to prediction, ours has a new element: there are two timescales, since the recent history changes at every step whereas regret accumulates more slowly.

Related papers

• Loss Shaping Constraints for Long-Term Time Series Forecasting [79.3533114027664]
  We present a Constrained Learning approach for long-term time series forecasting that respects a user-defined upper bound on the loss at each time-step. We propose a practical Primal-Dual algorithm to tackle it, and aims to demonstrate that it exhibits competitive average performance in time series benchmarks, while shaping the errors across the predicted window.
  arXiv  Detail & Related papers  (2024-02-14T18:20:44Z)
• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction [54.21695754082441]
  Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility. Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions. We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction. Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
  arXiv  Detail & Related papers  (2023-08-18T16:21:15Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)
• Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning [11.516147824168732]
  This paper aims to offer an approach using Twin-Delayed DDPG (TD3) and the daily close price in order to achieve a trading strategy in the stock and cryptocurrency markets. Both the stock (Amazon) and cryptocurrency (Bitcoin) markets are addressed in this research to evaluate the performance of the proposed algorithm.
  arXiv  Detail & Related papers  (2022-10-07T11:42:31Z)
• A Regret-Variance Trade-Off in Online Learning [14.41667013062914]
  We show how variance of predictions can be exploited in learning. In online prediction with corrupted losses, we show that the effect of corruption on the regret can be compensated by a large variance. We extend our results to the setting of online linear regression.
  arXiv  Detail & Related papers  (2022-06-06T14:50:19Z)
• Memory Bounds for the Experts Problem [53.67419690563877]
  Online learning with expert advice is a fundamental problem of sequential prediction. The goal is to process predictions, and make a prediction with the minimum cost. An algorithm is judged by how well it does compared to the best expert in the set.
  arXiv  Detail & Related papers  (2022-04-21T01:22:18Z)
• Online Search With Best-Price and Query-Based Predictions [2.3204178451683264]
  We study learning-augmented algorithms in which there is a potentially erroneous prediction concerning the input. We provide experimental results on data obtained from stock exchange markets.
  arXiv  Detail & Related papers  (2021-12-02T20:18:37Z)
• REST: Relational Event-driven Stock Trend Forecasting [76.08435590771357]
  We propose a relational event-driven stock trend forecasting (REST) framework, which can address the shortcoming of existing methods. To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts. To address the second shortcoming, we construct a stock graph and design a new propagation layer to propagate the effect of event information from related stocks.
  arXiv  Detail & Related papers  (2021-02-15T07:22:09Z)
• From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting [54.273455592965355]
  Uncertainty in future trajectories stems from two sources: (a) sources known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works.
  arXiv  Detail & Related papers  (2020-12-02T21:01:29Z)
• Online Prediction With History-Dependent Experts: The General Case [1.52292571922932]
  We study the problem of prediction of binary sequences with expert advice in the online setting, which is a classic example of online machine learning. We interpret the binary sequence as the price history of a stock, and view the predictor as the investor, which converts the problem into a stock prediction problem.
  arXiv  Detail & Related papers  (2020-07-31T19:40:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.