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 detects dangerous states in gridworlds using geometric defects.
Study uses geometric algebra to analyze credit cycles, revealing dangerous feedback loops.
Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a perfect expert and avoiding dangerous behaviors becomes relevant for safety reasons. We present the idea of \textit{learning to avoid}, an objective opposite to imitation learning …
This work improves deep reinforcement learning robustness to adversarial state uncertainty.
This document describes an approach to the problem of predicting dangerous seismic events in active coal mines up to 8 hours in advance. It was developed as a part of the AAIA'16 Data Mining Challenge: Predicting Dangerous Seismic Events in Active Coal Mines. The solutions presented consist of ensembles of various pred…
Develops a method to simulate rare dangerous events in autonomous systems.
IVMs help identify dangerous traffic conditions in real-time.
Scene understanding and semantic segmentation are at the core of many computer vision tasks, many of which, involve interacting with humans in potentially dangerous ways. It is therefore paramount that techniques for principled design of robust models be developed. In this paper, we provide analytic and empirical evide…
We apply contact homology to obtain new results in the problem of distinguishing immersed plane curves without dangerous self-tangencies.
Sepsis is a dangerous condition that is a leading cause of patient mortality. Treating sepsis is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we explore the use of continuous state-space mode…
Most microscopic pedestrian navigation models use the concept of "forces" applied to the pedestrian agents to replicate the navigation environment. While the approach could provide believable results in regular situations, it does not always resemble natural pedestrian navigation behaviour in many typical settings. In …
We consider tackling a single-agent RL problem by distributing it to learners. These learners, called advisors, endeavour to solve the problem from a different focus. Their advice, taking the form of action values, is then communicated to an aggregator, which is in control of the system. We show that the local plan…
We introduce a mathematical model on the dynamics of demand and supply incorporating collectability and saturation factors. Our analysis shows that when the fluctuation of the determinants of demand and supply is strong enough, there is chaos in the demand-supply dynamics. Our numerical simulation shows that such a cha…
A dangerously brief history of the developments of the main ideas in economics, as observed by a physicist, is given. This was published in 'Econophysics of Stock and Other Markets', Eds. A. Chatterjee, B. K. Chakrabarti, New Economic Windows Series, Springer, Milan, 2006, pp~219-224.
When the available statistical information is imperfect, it is dangerous to follow standard optimisation procedures to construct an optimal portfolio, which usually leads to a strong concentration of the weights on very few assets. We propose a new way, based on generalised entropies, to ensure a minimal degree of dive…
We address the problem of maintaining high voltage power transmission networks in security at all time, namely anticipating exceeding of thermal limit for eventual single line disconnection (whatever its cause may be) by running slow, but accurate, physical grid simulators. New conceptual frameworks are calling for a p…
Before deploying autonomous agents in the real world, we need to be confident they will perform safely in novel situations. Ideally, we would expose agents to a very wide range of situations during training, allowing them to learn about every possible danger, but this is often impractical. This paper investigates safet…
A recent line of work has uncovered a new form of data poisoning: so-called \emph{backdoor} attacks. These attacks are particularly dangerous because they do not affect a network's behavior on typical, benign data. Rather, the network only deviates from its expected output when triggered by a perturbation planted by an…
Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a result of some artifacts learned by the model instead of actual knowledge from the data. This paper f…
Survive method improves model-based RL by avoiding terminal states, reducing sample complexity.
Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We propose using oracle feedback to learn a predictive model of these blind spots to red…
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black…
Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics. However, a major challenge in training agents from learned reward models is that the agent can learn to exploit errors in the reward model to achieve high reward behaviors that do not correspond …
Economic integration, globalization and financial crises represent examples of processes whose understanding requires the analysis of the underlying network structure. Of particular interest is establishing whether a real economic network is in a state of (quasi)stationary equilibrium, i.e. characterized by smooth stru…
The so-called great divergence in the income per capita is described in the Unified Growth Theory as the mind-boggling and unresolved mystery about the growth process. This mystery has now been solved: the great divergence never happened. It was created by the manipulation of data. Economic growth in various regions is…
For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current methods for exact high confidence off-policy evaluation that use importance sampl…
Recently it's been shown that neural networks can use images of human faces to accurately predict Body Mass Index (BMI), a widely used health indicator. In this paper we demonstrate that a neural network performing BMI inference is indeed vulnerable to test-time adversarial attacks. This extends test-time adversarial a…
For autonomous agents to successfully operate in real world, the ability to anticipate future motions of surrounding entities in the scene can greatly enhance their safety levels since potentially dangerous situations could be avoided in advance. While impressive results have been shown on predicting each agent's behav…
Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret adversarial perturbations in terms of the effective input signal that classifiers …
Survey of algorithms for testing AI-driven CPS safety.
An important application of intelligent vehicles is advance detection of dangerous events such as collisions. This problem is framed as a problem of optimal alarm choice given predictive models for vehicle location and motion. Techniques for real-time collision detection are surveyed and grouped into three classes: ran…
CQL (ReDS) learns from varied driving behaviors, improving offline RL performance.
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…
RAFs Ensemble improves neural network uncertainty quantification.
This paper tackles over-certainty in test-time adaptation models, proposing a solution to improve calibration.
Year by year control of normal and emergency conditions of up-to-date power systems becomes an increasingly complicated problem. With the increasing complexity the existing control system of power system conditions which includes operative actions of the dispatcher and work of special automatic devices proves to be ins…
In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact the…
MOPO optimizes offline RL by penalizing dynamics uncertainty.
In autonomous vehicle (AV) control, allowing mistakes can be quite dangerous and costly in the real world. For this reason we investigate methods of training an AV without allowing the agent to explore and instead having a human explorer collect the data. Supervised learning has been explored for AV control, but it enc…
There is an increasing interest in estimating expectations outside of the classical inference framework, such as for models expressed as probabilistic programs. Many of these contexts call for some form of nested inference to be applied. In this paper, we analyse the behaviour of nested Monte Carlo (NMC) schemes, for w…
Interactive framework improves understanding of deep neural networks.
DeCom predicts post-COVID RSV timing and intensity with NPI consideration.
This paper evaluates debiasing methods on word embeddings to reduce religious bias.
Nowadays, advanced intrusion detection systems (IDSs) rely on a combination of anomaly detection and signature-based methods. An IDS gathers observations, analyzes behavioral patterns, and reports suspicious events for further investigation. A notorious issue anomaly detection systems (ADSs) and IDSs face is the possib…
This study uses TDA to map corporate failure, revealing distinct regions of risk.
Success conditioning optimizes policies by imitating successful trajectories, solving a trust-region optimization problem.
Notwithstanding almost forty years of efforts, the market for paintings still lacks a widely accepted price index. In this paper, we introduce a simple and intuitive metric to construct such index. Our metric is based on the price of a painting divided by its area. This formulation rests on a solid mathematical foundat…
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like black-box functions, but this mindset is especially dangerous when used for control…