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.
Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.
The study introduces backward baselines to distinguish past prediction from future prediction in machine learning models.
We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on…
Bayesian Scattering offers a simple baseline for image data uncertainty.
Investigates Q value evolution in Stable Baselines for DQL in simple vs complex environments.
Paper tackles online learning for DR management with incentives.
Like all sub-fields of machine learning Bayesian Deep Learning is driven by empirical validation of its theoretical proposals. Given the many aspects of an experiment it is always possible that minor or even major experimental flaws can slip by both authors and reviewers. One of the most popular experiments used to eva…
Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent ba…
Policy gradient methods are a widely used class of model-free reinforcement learning algorithms where a state-dependent baseline is used to reduce gradient estimator variance. Several recent papers extend the baseline to depend on both the state and action and suggest that this significantly reduces variance and improv…
Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in the uncertain state-action pairs, in order to control the variance on th…
Dark Experience improves continual learning with a simple, strong baseline.
Human language is a rich multimodal signal consisting of spoken words, facial expressions, body gestures, and vocal intonations. Learning representations for these spoken utterances is a complex research problem due to the presence of multiple heterogeneous sources of information. Recent advances in multimodal learning…
Patients initially diagnosed with early mild cognitive impairment (eMCI) are known to be a clinically heterogeneous group with very subtle patterns of brain atrophy. To examine the boarders between normal controls (NC) and eMCI, Magnetic Resonance Imaging (MRI) was extensively used as a non-invasive imaging modality to…
Study shows popular RL methods are inefficient due to unfair baselines.
This work establishes safe reinforcement learning for LQR with nonlinear baselines.
How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes in the environment, including the actions of other agents. To isolate the source…
Study identifies and analyzes spurious correlations in data-driven models.
Safe RL in linear systems achieves -regret.
A training-free conformal interval is a mandatory baseline for probabilistic time-series forecasting.
RL agents outperform baselines in asset allocation.
Node-perturbation learning is a type of statistical gradient descent algorithm that can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. It estimates the gradient of an objective function by using the change in the object function in response to the per…
New learned optimizers outperform baselines by incorporating known and novel mechanisms.
Paper compares two local explanation methods for machine learning models.
There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and without the need fora system model. However, the variance of the gradient estimator ha…
This work provides a strong baseline for the problem of multi-source multi-target domain adaptation and generalization in medical imaging. Using a diverse collection of ten chest X-ray datasets, we empirically demonstrate the benefits of training medical imaging deep learning models on varied patient populations for ge…
Proposes baselines for joint NAS and HPO optimization.
This paper presents the recently published Cerema AWP (Adverse Weather Pedestrian) dataset for various machine learning tasks and its exports in machine learning friendly format. We explain why this dataset can be interesting (mainly because it is a greatly controlled and fully annotated image dataset) and present base…
Paper formalizes continual semi-supervised anomaly detection, showing promising results.
Graphs are complex objects that do not lend themselves easily to typical learning tasks. Recently, a range of approaches based on graph kernels or graph neural networks have been developed for graph classification and for representation learning on graphs in general. As the developed methodologies become more sophistic…
We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT). To this end, we introduce a new baseline called Centroid Networks, a modification of Prototypical Networks in which the support set labels are hidden from the metho…
A simple baseline outperforms deep learning methods in transportation forecasting.
This work describes and discusses an algorithm submitted to the Sound Event Localization and Detection Task of DCASE2019 Challenge. The proposed methodology relies on parametric spatial audio analysis for source localization and detection, combined with a deep learning-based monophonic event classifier. The evaluation …
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
ApolloRL offers a platform for RL research in autonomous driving.
Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches …
New methods correct spectral distortions using known analyte concentrations.
Paper finds Dutch Draw optimal baseline for binary classification.
New algorithm improves online learning under performance constraints.
Study proposes learning optimal priors from data for better Bayesian inference.
Enhanced visual feature attribution via adaptive baseline weighting.
BASIS improves LLM reasoning by sharing batchwise rollout info, reducing MSE by 69%.
WiGS improves active learning for regression by dynamically selecting informative samples.
The paper reveals that baselines significantly impact RL algorithms' convergence.
Time series foundation models are well-calibrated, improving over baseline models.
New linear algorithms improve wSVMs for multiclass probability estimation.
New method FedEx accelerates federated hyperparameter tuning.
In this work we describe the preparation of a time series dataset of inertial measurements for determining the surface type under a wheeled robot. The data consists of over 7600 labeled time series samples, with the corresponding surface type annotation. This data was used in two public competitions with over 1500 part…
Enhances survival analysis by separating population behavior from individual dynamics.