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.
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in t…
Paper optimizes recommendation systems for long-term business metrics.
DBOT uses AI to automate long-term stock valuation.
It is suggested to consider long term trends of financial markets as a growth phenomenon. The question that is asked is what conditions are needed for a long term sustainable growth or contraction in a financial market? The paper discuss the role of traditional market players of long only mutual funds versus hedge fund…
Benchmark for math reasoning models from human proofs.
In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner would exploit model flaws, which can yield catastrophic failures. This paper focuse…
This paper proposes a framework to predict long-term trends and short-term fluctuations in multivariate time series.
New RNN model handles long-term dependencies in irregularly-sampled time series.
Bayesian model predicts interest rates with short-term accuracy and long-term stability.
A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason,…
Investigates long-term performance of multi-fidelity Bayesian optimization.
In this paper we examine a possible reason for the LSTM outperforming the GRU on language modeling and more specifically machine translation. We hypothesize that this has to do with counting. This is a consistent theme across the literature of long term dependence, counting, and language modeling for RNNs. Using the si…
Paper develops an attention mechanism for long-term scientific impact prediction.
It is a known fact that training recurrent neural networks for tasks that have long term dependencies is challenging. One of the main reasons is the vanishing or exploding gradient problem, which prevents gradient information from propagating to early layers. In this paper we propose a simple recurrent architecture, th…
PriceSeer benchmarks LLMs in real-time stock prediction.
Improves neural relational inference for dynamic multi-agent trajectories.
The bias potential model explains how generative models can generalize or memorize samples.
Bayesian model improves cure fraction estimation in survival analysis.
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are oft…
We develop a new nonparametric approach for estimating the risk-neutral density of asset prices and reformulate its estimation into a double-constrained optimization problem. We evaluate our approach using the S\&P 500 market option prices from 1996 to 2015. A comprehensive cross-validation study shows that our approac…
While LSTMs show increasingly promising results for forecasting Financial Time Series (FTS), this paper seeks to assess if attention mechanisms can further improve performance. The hypothesis is that attention can help prevent long-term dependencies experienced by LSTM models. To test this hypothesis, the main contribu…
PureTS uses simple linear models to improve long-term time series forecasting.
Benchmark tests LLMs on discovering physics laws in unconventional worlds.
We introduce here for the first time the long-term swap rate, characterised as the fair rate of an overnight indexed swap with infinitely many exchanges. Furthermore we analyse the relationship between the long-term swap rate, the long-term yield, see Biagini et al. [2018], Biagini and Härtel [2014], and El Karoui et a…
Kernel method estimates long-term effects from short-term data.
Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.
Model combines long-term and short-term memory using conceptors.
New framework estimates long-term outcomes from short-term data.
TimeBridge addresses non-stationarity in long-term time series forecasting.
TD-Flow improves long-term predictions in agent learning.
The choice of how to retain information about past gradients dramatically affects the convergence properties of state-of-the-art stochastic optimization methods, such as Heavy-ball, Nesterov's momentum, RMSprop and Adam. Building on this observation, we use stochastic differential equations (SDEs) to explicitly study t…
Peer review is the foundation of scientific publication, and the task of reviewing has long been seen as a cornerstone of professional service. However, the massive growth in the field of machine learning has put this community benefit under stress, threatening both the sustainability of an effective review process and…
This paper balances short-term and long-term rewards in policy learning.
This paper combines LLMs with RL for better trading strategies.
We study the long-term memory in diverse stock market indices and foreign exchange rates using the Detrended Fluctuation Analysis(DFA). For all daily and high-frequency market data studied, no significant long-term memory property is detected in the return series, while a strong long-term memory property is found in th…
Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the truncation bias, which drastically limits its ability to learn long-term dependenc…
This paper uses Bayesian models to analyze CTA returns across short and long-term trends.
Estimates long-term effects from short-term experiments and observational data with unobserved confounders.
The paper tackles long-term treatment effects with persistent confounders using sequential short-term outcomes.
TiDE uses MLP for fast, simple long-term time-series forecasting.
In this paper we provide compelling evidence of cyclical mean reversion and multiperiod stock return predictability over horizons of about 30 years with a half-life of about 15 years. This implies that the US stock market follows a long-term rhythm where a period of above average returns tends to be followed by a perio…
It is demonstrated that the US economy has on the long-term in reality been governed by the Keynesian approach to economics independent of the current official economical policy. This is done by calculating the two-point correlation function between the fluctuations of the DJIA and the US public debt. We find that the …
The paper proposes Tier Balancing for dynamic fairness in decision-making.
Paper proposes a model-free algorithm for CMDPs with long-term constraints, achieving optimal regret bounds.
The paper presents the comparative study of the nature of stock markets in short-term and long-term time scales with and without structural break in the stock data. Structural break point has been identified by applying Zivot and Andrews structural trend break model to break the original time series (TSO) into time ser…
Adherence can be defined as "the extent to which patients take their medications as prescribed by their healthcare providers"[Osterberg and Blaschke, 2005]. World Health Organization's reports point out that, in developed countries, only about 50% of patients with chronic diseases correctly follow their treatments. Thi…
Combining experimental and observational data for long-term causal effects.
The paper targets optimal interventions for long-term outcomes using imputed data and policy learning.