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.
The Neural Testbed evaluates joint predictions of neural agents, revealing their limitations.
Jelly Bean World tests never-ending learning in complex environments.
Myriad offers a testbed for integrating machine learning and trajectory optimization.
Study shows current image classification models lack robustness to real-world dataset shifts.
MDP Playground tests RL agents across various dimensions for better understanding and debugging.
We present a novel unsupervised deep learning approach that utilizes the encoder-decoder architecture for detecting anomalies in sequential sensor data collected during industrial manufacturing. Our approach is designed not only to detect whether there exists an anomaly at a given time step, but also to predict what wi…
SMEs provide a transparent testbed for RL evaluation.
The paper examines domain generalization algorithms and finds empirical risk minimization performs well.
DeepRacing uses neural networks to predict trajectories for autonomous racing in video games.
Developed causal chambers for AI validation, providing real-world data.
Proposes a real-time DDoS detection framework using machine learning.
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty arises from stochastic environments and must be accounted for in risk-sensitive applications. We highlight the challenges involved in simultan…
Infinitely wide neural nets perform well on small datasets.
We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best NN architecture for a given dataset, using the NAB metric to assess the quality…
Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics. It has been widely adopted in the research of robotics, autonomous driving, etc. Despite its popularity, there still lacks some sophist…
Synth-MIA assesses privacy leakage in synthetic tabular data models.
Incremental learning from non-stationary data poses special challenges to the field of machine learning. Although new algorithms have been developed for this, assessment of results and comparison of behaviors are still open problems, mainly because evaluation metrics, adapted from more traditional tasks, can be ineffec…
Paper presents a new dataset for testing causal discovery methods in industrial systems.
We present a general framework for classifying partially observed dynamical systems based on the idea of learning in the model space. In contrast to the existing approaches using model point estimates to represent individual data items, we employ posterior distributions over models, thus taking into account in a princi…
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extension…
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are often hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. We pres…
Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows over time. We propose a similarity-aware embedding matrix compression method call…
Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In this paper, we introduce an approach that integrates human strategies to increa…
Framework generates multimodal datasets with known MI for benchmarking.
This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental …
Paper proposes online learning for estimating AC network admittance matrix.
We create a large dataset for fact checking claims and improve prediction accuracy.
Paper uses agent-based simulation to identify investor types in financial markets.
Adversarial fog tests autonomous navigation models.
Benchmark evaluates financial misinformation detection models, revealing weaknesses without external context.
Graph hypernetworks improve molecule property prediction and classification.
Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been…
Managing the prediction of metrics in high-frequency financial markets is a challenging task. An efficient way is by monitoring the dynamics of a limit order book to identify the information edge. This paper describes the first publicly available benchmark dataset of high-frequency limit order markets for mid-price pre…
We introduce RSE to measure robustness in estimation problems.
PredictionMarketBench benchmarks trading agents on prediction markets.
A new method uses gene interaction networks to predict gene functions.
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged. In …
Knowledge tracing is a sequence prediction problem where the goal is to predict the outcomes of students over questions as they are interacting with a learning platform. By tracking the evolution of the knowledge of some student, one can optimize instruction. Existing methods are either based on temporal latent variabl…
Knowledge graphs, on top of entities and their relationships, contain other important elements: literals. Literals encode interesting properties (e.g. the height) of entities that are not captured by links between entities alone. Most of the existing work on embedding (or latent feature) based knowledge graph analysis …
Study detects and mitigates stealthy DDoS attacks in IoT networks.
Proposes a novel SAM operator for separate item and relational memories.
This paper analyzes CNNs for malware detection in cloud IaaS.
Research in deep reinforcement learning (RL) has coalesced around improving performance on benchmarks like the Arcade Learning Environment. However, these benchmarks conspicuously miss important characteristics like abrupt context-dependent shifts in strategy and temporal sensitivity that are often present in real-worl…
Clustering consists of grouping together samples giving their similar properties. The problem of modeling simultaneously groups of samples and features is known as Co-Clustering. This paper introduces ROCCO - a Robust Continuous Co-Clustering algorithm. ROCCO is a scalable, hyperparameter-free, easy and ready to use al…
DyFEn simulates blockchain for fee setting in payment channels.
Neural Markov models improve time series analysis by balancing deep learning and classical models.
Open problem: Establishing bounds for Cayley-table completion to discover discrete algorithmic axioms.
More than 50 years ago Bongard introduced 100 visual concept learning problems as a testbed for intelligent vision systems. These problems are now known as Bongard problems. Although they are well known in the cognitive science and AI communities only moderate progress has been made towards building systems that can so…