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.
Model predicts human food choices based on demographics.
Aims to learn from multiple unpredictable teachers with minimal interaction.
In this work we present a modified neural network model which is capable to simulate Markov Chains. We show how to express and train such a network, how to ensure given statistical properties reflected in the training data and we demonstrate several applications where the network produces non-deterministic outcomes. On…
RegFlow models future states with flexible probability distributions.
This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by controlling the improvements' stochasticity. Additionally we show that a suitable represe…
New method ensures consistent inference across different tensor parallel sizes for large language models.
The paper uses a novel framework to learn option prices by imitating principal investor behavior.
LLMs produce volatile sentence-level sentiment classifications that affect financial decision-making.
We study optimal solutions to an abstract optimization problem for measures, which is a generalization of classical variational problems in information theory and statistical physics. In the classical problems, information and relative entropy are defined using the Kullback-Leibler divergence, and for this reason optim…
Developed mlf-core for deterministic machine learning.
New method calculates Shapley values for uncertain functions.
Analyzes how rough volatility affects stock pricing and risk premium.
This paper tackles reliability analysis for stochastic systems using surrogate models.
We show that the stochasticity in training ResNets for image classification on GPUs in TensorFlow is dominated by the non-determinism from GPUs, rather than by the initialisation of the weights and biases of the network or by the sequence of minibatches given. The standard deviation of test set accuracy is 0.02 with fi…
A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Seque…
In this paper, we use an aerial base station (aerial-BS) to enhance fairness in a dynamic environment with user mobility. The problem of optimally placing the aerial-BS is a non-deterministic polynomial-time hard (NP-hard) problem. Moreover, the network topology is subject to continuous changes due to the user mobility…
We apply our statistically deterministic machine learning/clustering algorithm *K-means (recently developed in https://ssrn.com/abstract=2908286) to 10,656 published exome samples for 32 cancer types. A majority of cancer types exhibit mutation clustering structure. Our results are in-sample stable. They are also out-o…
DiAMoNDBack models protein backmapping from coarse-grained Cα traces.
There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and without the need fora system model. However, the variance of the gradient estimator ha…
We show a concise extension of the monotone stability approach to backward stochastic differential equations (BSDEs) that are jointly driven by a Brownian motion and a random measure for jumps, which could be of infinite activity with a non-deterministic and time inhomogeneous compensator. The BSDE generator function c…
We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encoura…
Standard practice in training neural networks involves initializing the weights in an independent fashion. The results of recent work suggest that feature "diversity" at initialization plays an important role in training the network. However, other initialization schemes with reduced feature diversity have also been sh…
This paper highlights new opportunities for designing large-scale machine learning systems as a consequence of blurring traditional boundaries that have allowed algorithm designers and application-level practitioners to stay -- for the most part -- oblivious to the details of the underlying hardware-level implementatio…
Batch normalization with regularization turns deterministic autoencoders into generative models.
In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^-4) differences for state-of-the-art systems. For …
CGAN fails to improve deterministic sequence predictions, revealing a theoretical limitation.
In reinforcement learning episodes, the rewards and punishments are often non-deterministic, and there are invariably stochastic elements governing the underlying situation. Such stochastic elements are often numerous and cannot be known in advance, and they have a tendency to obscure the underlying rewards and punishm…
New method shows random, diverse initializations are not essential for deep neural networks.
A new method embeds data using Gaussian processes based on the heat kernel.
Recent studies in the field of human vision science suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. Based on this knowledge, we propose a new stochastic model of visual attention by introducing…
Recent breakthroughs in the field of deep learning have led to advancements in a broad spectrum of tasks in computer vision, audio processing, natural language processing and other areas. In most instances where these tasks are deployed in real-world scenarios, the models used in them have been shown to be susceptible …
Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual transformations, constructing and tuning the more sophisticated compositions typically…
The premorbid geometry of the mandible is of significant relevance in jaw reconstructive surgeries and occasionally unknown to the surgical team. In this paper, an optimization framework is introduced to train deep models for completion (reconstruction) of the missing segments of the bone based on the remaining healthy…
New method handles large reward variations in reinforcement learning.
Study shows computational and statistical gaps in Gaussian Single-Index Models.
Deep learning model estimates uncertainty in complex regression tasks.
In both the fields of computer science and medicine there is very strong interest in developing personalized treatment policies for patients who have variable responses to treatments. In particular, I aim to find an optimal personalized treatment policy which is a non-deterministic function of the patient specific cova…
A new graphical method compares stochastic variables visually.
This work improves understanding of dimension reduction algorithms and their probabilistic embeddings.
In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of losses into prior hidden states and inputs held in memory. This allows gradients to f…
This paper presents a technique for reduced-order Markov modeling for compact representation of time-series data. In this work, symbolic dynamics-based tools have been used to infer an approximate generative Markov model. The time-series data are first symbolized by partitioning the continuous measurement space of the …
Model forecasts motor vehicle collision rates with high accuracy.
Improved tensor rank learning for CPD models using a generalized hyperbolic prior.
Model captures neural activity related to behavior while separating internal computations.
Behavior modification improves prediction accuracy by nudging user behavior.
LISBET automates social behavior analysis using machine learning.
The paper introduces new metrics for evaluating generative models of behavior.
Mobile phones can record individual's daily behavioral data as a time-series. In this paper, we present an effective time-series segmentation technique that extracts optimal time segments of individual's similar behavioral characteristics utilizing their mobile phone data. One of the determinants of an individual's beh…