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.
Kernel for STL formulae enables machine learning in temporal logic.
Algorithm mines environment assumptions for cyber-physical systems.
Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.
This paper improves STL inference reliability under covariate shift.
Signal temporal logic (STL) is an expressive language to specify time-bound real-world robotic tasks and safety specifications. Recently, there has been an interest in learning optimal policies to satisfy STL specifications via reinforcement learning (RL). Learning to satisfy STL specifications often needs a sufficient…
Combines neural networks and STL for multi-class time-series classification.
This work improves safety validation of autonomous vehicles by finding interpretable failures.
Transformers learn to predict temporal logic solutions from classical solver outputs.
Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data. Designers often look for tools to help classify and categorize the data. Traditional machine learning techniques for time-series data offer several solutions to solve these …
Safe reinforcement learning with logical constraints for optimal policy synthesis.
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Neuro-symbolic agent learns systematic generalisation from formal instructions.
This paper tackles spatio-temporal information preservation in machine learning.
This paper introduces a new reward shaping method for average-reward reinforcement learning.
Develops a new model for controllable and realistic traffic simulation.
Quantum Signal Processing reduces derivative pricing quantum resource requirements.
We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including "safety") that…
ProbKT uses probabilistic logical reasoning to train object detection models with weak supervision.
We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct …
We address the problem of learning human-interpretable descriptions of a complex system from a finite set of positive and negative examples of its behavior. In contrast to most of the recent work in this area, which focuses on descriptions expressed in Linear Temporal Logic (LTL), we develop a learning algorithm for fo…
RDLI integrates domain logic and context grounding to detect crypto anomalies under scarce labels.
It is notoriously difficult to control the behavior of reinforcement learning agents. Agents often learn to exploit the environment or reward signal and need to be retrained multiple times. The multi-objective reinforcement learning (MORL) framework separates a reward function into several objectives. An ideal MORL age…
Due to the dynamic nature, chaotic time series are difficult predict. In conventional signal processing approaches signals are treated either in time or in space domain only. Spatio-temporal analysis of signal provides more advantages over conventional uni-dimensional approaches by harnessing the information from both …
FreST Loss decorrelates spatio-temporal dependencies in graph signals.
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables…
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL algorithm to synthesize control policies that maximize the probability of satisfying h…
Unified model learns concepts across domains like left and right.
Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsule…
Neural signals are characterized by rich temporal and spatiotemporal dynamics that reflect the organization of cortical networks. Theoretical research has shown how neural networks can operate at different dynamic ranges that correspond to specific types of information processing. Here we present a data analysis framew…
Financial markets modeled like brain networks using dMNC.
The paper shows averaging gradients leads to memorization, proposing an alternative algorithm to focus on invariances.
A new neural network captures and explains trajectory patterns.
This paper addresses the energy disaggregation problem, i.e. decomposing the electricity signal of a whole home to its operating devices. First, we cast the problem as a dictionary learning (DL) problem where the key electricity patterns representing consumption behaviors are extracted for each device and stored in a d…
Most current methods for learning from demonstrations assume that those demonstrations alone are sufficient to learn the underlying task. This is often untrue, especially if extra safety specifications exist which were not present in the original demonstrations. In this paper, we allow an expert to elaborate on their o…
We describe a new framework for causal inference and its application to return time series. In this system, causal relationships are represented as logical formulas, allowing us to test arbitrarily complex hypotheses in a computationally efficient way. We simulate return time series using a common factor model, and sho…
In kernel methods, temporal information on the data is commonly included by using time-delayed embeddings as inputs. Recently, an alternative formulation was proposed by defining a gamma-filter explicitly in a reproducing kernel Hilbert space, giving rise to a complex model where multiple kernels operate on different t…
HRTPP improves TPP interpretability and accuracy in medical event modeling.
ST-GCN improves rs-fMRI prediction accuracy by modeling spatio-temporal graph connectivity.
This letter extends the concept of graph-frequency to graph signals that evolve with time. Our goal is to generalize and, in fact, unify the familiar concepts from time- and graph-frequency analysis. To this end, we study a joint temporal and graph Fourier transform (JFT) and demonstrate its attractive properties. We b…
We have developed an efficient algorithm for the maximum likelihood joint tracking and association problem in a strong clutter for GMTI data. By using an iterative procedure of the dynamic logic process "from vague-to-crisp," the new tracker overcomes combinatorial complexity of tracking in highly-cluttered scenarios a…
Temporal Causal Prior-Data Fitted Networks (TCPFN) for industrial time series causal discovery
Improving the performance of click-through rate (CTR) prediction remains one of the core tasks in online advertising systems. With the rise of deep learning, CTR prediction models with deep networks remarkably enhance model capacities. In deep CTR models, exploiting users' historical data is essential for learning user…
Temporal Functional Circuits explain KAN forecasts with interpretable edge functions.
TNC learns time series representations by leveraging temporal neighborhoods.
AlphaLogics mines market logic to generate interpretable alpha factors.
Certified guidance ensures generative models always meet planning objectives.
We address the sparse signal recovery problem in the context of multiple measurement vectors (MMV) when elements in each nonzero row of the solution matrix are temporally correlated. Existing algorithms do not consider such temporal correlations and thus their performance degrades significantly with the correlations. I…
Proposes a GNN for multivariate time-series prediction with filtering.