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.
Gradient codes adapt to varying straggler counts in distributed learning.
Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with limited computation and storage requires streamlined methodologies that can effi…
E-scores assess LLM outputs for correctness, addressing p-hacking issues.
New framework identifies strongly identifiable models from flexible generators.
We introduce a differential geometric framework for describing families of quantum error-correcting codes and for understanding quantum fault tolerance. This work unifies the notion of topological fault tolerance with fault tolerance in other kinds of quantum error-correcting codes. In particular, we use fibre bundles …
Environmental stresses such as drought and heat can cause substantial yield loss in agriculture. As such, hybrid crops that are tolerant to drought and heat stress would produce more consistent yields compared to the hybrids that are not tolerant to these stresses. In the 2019 Syngenta Crop Challenge, Syngenta released…
Study examines how risk tolerance impacts long-term investment returns.
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., -perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse …
Fault-tolerant neural networks inspired by biological error correction codes.
Paper addresses fault-tolerance in distributed machine learning with stochastic gradient descent.
Open-source Vizier optimizes complex systems for Google and beyond.
QR-MIX models joint state-action values as a distribution to handle randomness in MARL.
This paper reviews quantum machine learning from NISQ to fault tolerance.
The next generation of AI applications will continuously interact with the environment and learn from these interactions. These applications impose new and demanding systems requirements, both in terms of performance and flexibility. In this paper, we consider these requirements and present Ray---a distributed system t…
Specialists tolerate defects to gain flexibility, which can be removed when needed.
Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robu…
Methods for prediction and tolerance intervals in non-normal models.
The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.
New method learns robustly with less data, bridging theory and practice.
The study formalizes temporal precision and recall for anomaly detection in sequences.
We introduce a simple framework for designing private boosting algorithms. We give natural conditions under which these algorithms are differentially private, efficient, and noise-tolerant PAC learners. To demonstrate our framework, we use it to construct noise-tolerant and private PAC learners for large-margin halfspa…
We develop and evaluate tolerance interval methods for dynamic treatment regimes (DTRs) that can provide more detailed prognostic information to patients who will follow an estimated optimal regime. Although the problem of constructing confidence intervals for DTRs has been extensively studied, prediction and tolerance…
Study on AI-driven modeling for high burnup accident-tolerant fuels in SMRs.
New method reduces sample complexity for robust learning.
Paper formalizes Simon's satisficing through FFSD, proving its equivalence to expected utility theory.
Split conformal prediction provides finite-sample guarantees for black-box models without distributional assumptions.
Study efficient learning of halfspaces with constant noise tolerance.
In real-world applications of reinforcement learning (RL), noise from inherent stochasticity of environments is inevitable. However, current policy evaluation algorithms, which plays a key role in many RL algorithms, are either prone to noise or inefficient. To solve this issue, we introduce a novel policy evaluation a…
Model shows how heterogeneity in strategies and risk tolerance affects financial market stability.
SignSGD improves distributed learning by tolerating faulty devices, including Byzantine adversaries.
ADGAN improves risk tolerance prediction by aligning cross-domain data.
We develop and analyze an asynchronous algorithm for distributed convex optimization when the objective writes a sum of smooth functions, local to each worker, and a non-smooth function. Unlike many existing methods, our distributed algorithm is adjustable to various levels of communication cost, delays, machines compu…
We consider the problem of engineering robust direct perception neural networks with output being regression. Such networks take high dimensional input image data, and they produce affordances such as the curvature of the upcoming road segment or the distance to the front vehicle. Our proposal starts by allowing a neur…
New insights into distribution testing with tolerance.
Algorithms optimize fair portfolios for diverse risk-tolerant consumers.
Improved analysis for nonconvex SGD methods with flexible sampling.
We consider distributed on-device learning with limited communication and security requirements. We propose a new robust distributed optimization algorithm with efficient communication and attack tolerance. The proposed algorithm has provable convergence and robustness under non-IID settings. Empirical results show tha…
The loss of a few neurons in a brain rarely results in any visible loss of function. However, the insight into what "few" means in this context is unclear. How many random neuron failures will it take to lead to a visible loss of function? In this paper, we address the fundamental question of the impact of the crash of…
Paper introduces Lambda EVaR, a new risk measure.
With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems. However, despite their impressive performance on "known inputs", these NNs can fail absurdly on the "unseen inputs", especially if these real…
Deep Learning Accelerators are prone to faults which manifest in the form of errors in Neural Networks. Fault Tolerance in Neural Networks is crucial in real-time safety critical applications requiring computation for long durations. Neural Networks with high regularisation exhibit superior fault tolerance, however, at…
Finding efficient decoders for quantum error correcting codes adapted to realistic experimental noise in fault-tolerant devices represents a significant challenge. In this paper we introduce several decoding algorithms complemented by deep neural decoders and apply them to analyze several fault-tolerant error correctio…
We analyze a nonlinear equation proposed by F. Black (1968) for the optimal portfolio function in a log-normal model. We cast it in terms of the risk tolerance function and provide, for general utility functions, existence, uniqueness and regularity results, and we also examine various monotonicity, concavity/convexity…
Paper proposes FTT-NAS to create fault-tolerant CNNs for edge devices.
We study a portfolio optimization problem for competitive agents with CRRA utilities and a common finite time horizon. The utility of an agent depends not only on her absolute wealth and consumption but also on her relative wealth and consumption when compared to the averages among the other agents. We derive a closed …
Novel method solves group synchronization with robust corruption tolerance.
Mango automates hyperparameter tuning for large-scale ML training.
RieCUR improves Robust PCA by combining Riemannian optimization and CUR decompositions.