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.
New method improves combinatorial optimization by overcoming inefficient sampling.
The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computationally expensive. More advanced methods like Population Based Training that learn optimal schedule…
Paper proposes DAC-ML, a cognitive architecture that learns quickly from few episodes.
Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren't just faster learners than their sample-inefficient deep learning (DL) and reinforcement learning (RL) brethren, but that they actually pursue fundamentally different learnin…
Study finds cryptoasset markets inefficient due to capital reallocation frictions.
Study minimizes market inefficiency in systemic economies.
New method improves meta-reinforcement learning efficiency.
Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead. Despite providing large improvements in wall-clock time, ES is data inefficient whe…
This paper shows how diverse tasks can make inefficient exploration in MTRL efficient.
Current approaches to amortizing Bayesian inference focus solely on approximating the posterior distribution. Typically, this approximation is, in turn, used to calculate expectations for one or more target functions - a computational pipeline which is inefficient when the target function(s) are known upfront. In this …
AGAC uses an adversary to enhance exploration in complex tasks.
Efficiently handles contextual bandits with diffusion models.
Variational Bayesian inference and (collapsed) Gibbs sampling are the two important classes of inference algorithms for Bayesian networks. Both have their advantages and disadvantages: collapsed Gibbs sampling is unbiased but is also inefficient for large count values and requires averaging over many samples to reduce …
Improved CEM for fast real-time planning in high-dimensional control tasks.
We study the effects of introducing information inefficiency in a model for a random linear economy with a representative consumer. This is done by considering statistical, instead of classical, economic general equilibria. Employing two different approaches we show that inefficiency increases the consumption set of a …
Study reveals inefficiencies in EU carbon trading market.
Social learning can make financial markets inefficient, but individual learning can fix this.
Study confirms mispricing in sportsbooks but finds data issues affect results.
Efficiently learns tree-structured Ising models with minimal samples.
Hamiltonian Monte Carlo on ReLU networks is inefficient due to large local error.
Can we make Bayesian posterior MCMC sampling more efficient when faced with very large datasets? We argue that computing the likelihood for N datapoints in the Metropolis-Hastings (MH) test to reach a single binary decision is computationally inefficient. We introduce an approximate MH rule based on a sequential hypoth…
Investors trade based on shifting prices, leading to market inefficiencies.
Improved reinforcement learning in Minecraft with human demonstrations.
Inefficient markets allow investors to consistently outperform the market. To demonstrate that inefficiencies exist in sports betting markets, we created a betting algorithm that generates above market returns for the NFL, NBA, NCAAF, NCAAB, and WNBA betting markets. To formulate our betting strategy, we collected and …
I summarize the recent work on market (in)efficiency, highlighting key elements why financial markets will never be made efficient. My approach is not by adding more empirical evidence, but giving plausible reasons as to where inefficiency arises and why it's not rational to arbitrage it away.
AdamCB optimizes neural network training by adaptively selecting samples.
The efficient market hypothesis has been considered one of the most controversial arguments in finance, with the academia divided between who claims the impossibility of beating the market and who believes that it is possible to gain over the average profits. If the hypothesis holds, it means, as suggested by Burton Ma…
Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-training) on other related tasks. In this work, we propose a technique to achieve such knowledge transfer in cases where agent trajectories conta…
Importance sampling has become an important tool for the computation of tail-based risk measures. Since such quantities are often determined mainly by rare events standard Monte Carlo can be inefficient and importance sampling provides a way to speed up computations. This paper considers moderate deviations for the wei…
Study shows popular RL methods are inefficient due to unfair baselines.
To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we explore different task scheduling approaches. We first consider existing non-adapti…
Imitation from observation is the framework of learning tasks by observing demonstrated state-only trajectories. Recently, adversarial approaches have achieved significant performance improvements over other methods for imitating complex behaviors. However, these adversarial imitation algorithms often require many demo…
FedSTaS stratifies and samples clients for efficient FL.
Study finds Bitcoin market efficient, no exploitable inefficiencies with neural networks.
A plane curve is a knot diagram in which each crossing is replaced by a 4-valent vertex, and so are dual to a subset of planar quadrangulations. The aim of this paper is to introduce a new tool for sampling diagrams via sampling of plane curves. At present the most efficient method for sampling diagrams is rejection sa…
ACE improves counterfactual explanations with fewer model queries.
LSAM optimizes deep learning training with improved efficiency.
RPO uses past and future state-action info for better policy optimization.
Calibrated Prediction-Powered Inference improves semisupervised mean estimation by calibrating prediction scores.
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. I…
Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization. Towards the sample-efficient RL, we propose ranking policy gradient (RPG), a policy …
Improves GAN sample quality by refining the training dataset.
Determinantal point processes (DPPs) are an important concept in random matrix theory and combinatorics. They have also recently attracted interest in the study of numerical methods for machine learning, as they offer an elegant "missing link" between independent Monte Carlo sampling and deterministic evaluation on reg…
Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models. While tremendous progresses have been achieved via scalable Bayesian sampling such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD)…
We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample…
We propose a novel sampling framework for inference in probabilistic models: an active learning approach that converges more quickly (in wall-clock time) than Markov chain Monte Carlo (MCMC) benchmarks. The central challenge in probabilistic inference is numerical integration, to average over ensembles of models or unk…
A new method for student-initiated action advice using novelty detection.
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient algorithms that perform updates using on-policy samples. The price of such ineffici…