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.
Guided Learning improves end-to-end modeling for multi-stage decision-making.
Paper identifies a shared toolkit of strategies for risk management across fields.
Introduces Conditional Action Trees to simplify RL action spaces.
The paper proposes a fair reinforcement learning framework to prevent healthcare disparities.
Paper proposes a method to quantify and explain machine learning uncertainty in predictive process monitoring.
Improves disentangled representation learning with multi-stage modeling.
Bayesian optimization tackles expensive cascade processes.
Paper introduces a multi-stage influence function to track model predictions.
This paper develops a learning framework for optimal strategies in multi-stage decentralized matching markets.
Multi-stage financial decision optimization under uncertainty depends on a careful numerical approximation of the underlying stochastic process, which describes the future returns of the selected assets or asset categories. Various approaches towards an optimal generation of discrete-time, discrete-state approximations…
In this paper, we consider multi-stage stochastic optimization problems with convex objectives and conic constraints at each stage. We present a new stochastic first-order method, namely the dynamic stochastic approximation (DSA) algorithm, for solving these types of stochastic optimization problems. We show that DSA c…
CSAC enables cooperative reinforcement learning for multi-stage tasks.
Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, co…
Motivated by the problem of computer-aided detection (CAD) of pulmonary nodules, we introduce methods to propagate and fuse uncertainty information in a multi-stage Bayesian convolutional neural network (CNN) architecture. The question we seek to answer is "can we take advantage of the model uncertainty provided by one…
New method designs experiments robustly for nonlinear estimation, improving parameter knowledge.
Improved online AED models with multi-stage training and multi-task learning.
Estimates and infers multi-stage stationary treatment policies with variable selection.
Improves classifier performance in multi-stage selection processes.
Adaptive multi-stage density ratio estimation improves learning of latent space EBM.
Paper presents a deep learning framework for faster, more accurate nuclear reactor power prediction.
Improves classifier performance in multi-stage processes with adversarial autoencoders and multi-task learning.
Estimates time-varying network connections using multi-stage smoothing.
This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL) method. Firstly, the principles of RL are introduced. Then, the Multi-Stage Cascading Failure (MSCF) problem is presented and its challenges are investigated. The problem is then tackled by the RL based on DC-OPF (Optimal P…
Deep neural networks can grok better than shallow ones, showing multi-stage generalization.
Study uses deep neural networks for causal inference tasks, especially in high-dimensional settings.
A number of recent work studied the effectiveness of feature selection using Lasso. It is known that under the restricted isometry properties (RIP), Lasso does not generally lead to the exact recovery of the set of nonzero coefficients, due to the looseness of convex relaxation. This paper considers the feature selecti…
"Feint Attack", as a new type of APT attack, has become the focus of attention. It adopts a multi-stage attacks mode which can be concluded as a combination of virtual attacks and real attacks. Under the cover of virtual attacks, real attacks can achieve the real purpose of the attacker, as a result, it often caused hu…
This work improves speech enhancement using multiple GAN generators in stages.
In many classification systems, sensing modalities have different acquisition costs. It is often {\it unnecessary} to use every modality to classify a majority of examples. We study a multi-stage system in a prediction time cost reduction setting, where the full data is available for training, but for a test example, m…
Neural network with data augmentation improves multi-stage pump prediction accuracy.
Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand. In contrast, model-free reinforcement learning (RL) can acquire behaviors from l…
This paper presents a simple method for a posteriori (historical) multi-variate multi-stage optimal trading under transaction costs and a diversification constraint. Starting from a given amount of money in some currency, we analyze the stage-wise optimal allocation over a time horizon with potential investments in mul…
Owing to the ever-increasing demand in wireless spectrum, Cognitive Radio (CR) was introduced as a technique to attain high spectral efficiency. As the number of secondary users (SUs) connecting to the cognitive radio network is on the rise, there is an imminent need for centralized algorithms that provide high through…
We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects. This problem presents a number of major challenges. Video demonstrations without teleoperation are easy for humans to…
One of the challenges in computational acoustics is the identification of models that can simulate and predict the physical behavior of a system generating an acoustic signal. Whenever such models are used for commercial applications an additional constraint is the time-to-market, making automation of the sound design …
Multi-task sparse feature learning aims to improve the generalization performance by exploiting the shared features among tasks. It has been successfully applied to many applications including computer vision and biomedical informatics. Most of the existing multi-task sparse feature learning algorithms are formulated a…
New method predicts and optimizes test-time scaling for LLMs.
New methods solve complex financial equations.
In this paper, we introduce multi-task learning (MTL) to data harmonization (DH); where we aim to harmonize images across different acquisition platforms and sites. This allows us to integrate information from multiple acquisitions and improve the predictive performance and learning efficiency of the harmonization mode…
The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our…
Multi-task feature learning aims to identity the shared features among tasks to improve generalization. It has been shown that by minimizing non-convex learning models, a better solution than the convex alternatives can be obtained. Therefore, a non-convex model based on the capped- regularization wa…
The paper introduces a privacy-preserving method for estimating treatment effects that maintains accuracy.
New insights into how to inspect and learn from multi-stage processes and AI reasoning.
Strategic valuation of efficient and well-timed network investments under uncertain electricity market environment has become increasingly challenging, because there generally exist multiple interacting options in these investments, and failing to systematically consider these options can lead to decisions that underva…
We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learni…
Combines k-means and hill climbing for stratification and allocation.
Two-stage framework detects multi-modal outliers.
Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.