Paper shows comparing single performance scores is insufficient for non-deterministic systems, proposing to compare score distributions.
problem Insufficient comparison of non-deterministic sequence tagging systems.
method Compare score distributions based on multiple executions of LSTM-networks.
result LSTM-networks produce superior and more stable performance when compared using score distributions.
Modified neural network models Markov Chains for non-deterministic outcomes.
problem Simulating non-deterministic behavior in neural networks.
method Developed a modified neural network model capable of simulating Markov Chains.
result Demonstrated the network's ability to produce non-deterministic outcomes.
RegFlow models future states with flexible probability distributions.
problem Predicting future states under complex, non-deterministic scenarios.
method Hypernetwork architecture and continuous normalizing flow model.
result RegFlow achieves state-of-the-art results on benchmark datasets.
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…
Aims to learn from multiple unpredictable teachers with minimal interaction.
problem Learning from multiple non-deterministic teachers with low interaction cost.
method Develops a framework and an active learning algorithm to estimate a distribution over policy space.
result Significantly reduces interaction with teachers without compromising performance.
Model predicts human food choices based on demographics.
problem Predicting human food choices from demographic data.
method Non-deterministic model based on NHANES dataset and behavioral studies.
result Generates synthetic data similar to original dataset.
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…
New method ensures consistent inference across different tensor parallel sizes for large language models.
problem Non-deterministic inference in large language models due to inconsistent reduction orders across GPUs.
method Tree-Based Invariant Kernels (TBIK) that align intra- and inter-GPU reduction orders through a unified hierarchical binary tree structure.
result Bit-wise identical results across different tensor parallel sizes for RL training.
LLMs produce volatile sentence-level sentiment classifications that affect financial decision-making.
problem Volatile outputs from LLMs impact financial text understanding tasks.
method Case study on US equity market investing via news sentiment analysis.
result Volatile LLM outputs lead to significant variations in portfolio construction and returns.
Neural painters learn to generate brushstrokes from a non-deterministic painting program.
problem Training an agent to generate realistic brushstrokes from a non-differentiable painting program.
method A differentiable neural painter model trained on brushstrokes, optimizing for human-like strokes and intrinsic style transfer.
result Direct optimization of brushstrokes can visualize ImageNet categories and generate ideal paintings.
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.
problem Ensuring machine learning models are deterministic for verification.
method Formulated requirements, developed mlf-core ecosystem, tested various models.
result Demonstrated deterministic models in biomedical fields.
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…
This paper tackles reliability analysis for stochastic systems using surrogate models.
problem Traditional reliability analysis relies on deterministic models, which are not suitable for stochastic systems with non-repeatable outcomes.
method The paper introduces reliability analysis for stochastic models by using generalized lambda models and stochastic polynomial chaos expansions as surrogate models to lower computational cost.
result The surrogate models enable efficient uncertainty quantification at a lower cost than traditional Monte Carlo simulation.
New method calculates Shapley values for uncertain functions.
problem Uncertain value functions in explainable machine learning.
method Definition of Shapley values using probability theory.
result Shapley values can be applied to uncertain functions.
Analyzes how rough volatility affects stock pricing and risk premium.
problem Impact of non-deterministic volatility risk on stock pricing.
method Rough volatility model under historical measure, analysis of stochastic volatility risk.
result Impact of non-deterministic volatility risk on pricing is significant.
DiAMoNDBack models protein backmapping from coarse-grained Cα traces.
problem Restoring all-atom details from coarse-grained protein representations.
method Autoregressive denoising diffusion model for residue-by-residue backmapping.
result Achieves state-of-the-art reconstruction performance in diverse applications.
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…
Non-determinism from GPUs dominates ResNet training accuracy variability.
problem Variability in ResNet training accuracy due to GPU non-determinism.
method Analysis of TensorFlow ResNet training on GPUs, comparing fixed seeds vs. different seeds.
result 74% of ResNet model variability is due to GPU non-determinism.
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…
StackSeq2Seq improves route finding on graphs using deep neural networks.
problem Finding the shortest path between graph nodes.
method Dual Encoder Seq2Seq architecture, context vector, homotopy continuation.
result Increased accuracy in learning shortest routes on graphs.
Batch normalization with regularization turns deterministic autoencoders into generative models.
problem Creating generative models from deterministic autoencoders.
method Using batch normalization as a source of non-determinism and adding entropic regularization.
result Deterministic autoencoders can be transformed into generative models with similar performance to variational autoencoders.
Decides if elements in free groups are primitive in polynomial time.
problem Deciding if elements in free groups are primitive.
method Non-deterministic polynomial time algorithm for general r; deterministic polynomial time for r=2. result Decidability of compressed primitivity problem in free groups.
CGAN fails to improve deterministic sequence predictions, revealing a theoretical limitation.
problem Improving deterministic sequence predictions with CGAN.
method Developed an adversarial content loss approach.
result CGAN does not improve deterministic sequence predictions.
Machine learning clusters mutations in cancer exomes, improving diagnostic speed and cost.
problem Extracting stable mutation structures from cancer exome data for early diagnostics.
method Statistically deterministic machine learning algorithm *K-means applied to exome samples.
result Majority of cancer types exhibit stable mutation clustering, while NMF methods are unstable.
Paper proposes Q-learning for efficient aerial BS placement to improve fairness in mobile networks.
problem Optimal placement of aerial base stations to enhance fairness in a dynamic user mobility environment.
method Reinforcement learning approach to solve the NP-hard problem of 3D placement.
result Simulation results show increased fairness among users with a reasonable computing time and solution close to optimal.
New method shows random, diverse initializations are not essential for deep neural networks.
problem The necessity of random, diverse initializations in deep neural networks.
method Constructed a deep convolutional network with identical features by initializing weights to 0, enabling signal propagation and stable gradients.
result Random, diverse initializations are not necessary for training neural networks.
A new method embeds data using Gaussian processes based on the heat kernel.
problem Embedding high-dimensional data in a low-dimensional space.
method Computing embeddings based on the Karhunen-Loève expansion of the heat kernel.
result The embedding approximates diffusion distances and is robust to outliers.
New findings show that minimal feature diversity at neural network initialization is harmful but can be mitigated with noise.
problem The importance of feature diversity at neural network initialization.
method A series of experiments comparing different initialization schemes, including adding noise.
result Minimal feature diversity is harmful but can be mitigated with noise, even standard GPU noise is sufficient.
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…
Paper tackles stochastic reinforcement learning with reduced observation costs.
problem Non-deterministic rewards and punishments with stochastic elements.
method Explicitly models stochastic elements and learning costs.
result Quantitative analysis of learning success criteria and observation cost probabilities.
Paper develops a method for compact Markov modeling of time series data.
problem Compact representation of time-series data with reduced memory.
method Symbolic dynamics for partitioning, hierarchical clustering for state representation, Bayesian inference for parameter identification.
result Reduced-order Markov models capture system dynamics with minimal memory.
A new neural network model enhances adversarial robustness without sacrificing task performance.
problem Adversarial attacks on neural networks deployed in real-world scenarios.
method Proposes a novel neural network paradigm where each parameter is modeled as a statistical distribution with learnable parameters.
result Demonstrates highly robust performance to various adversarial attacks while maintaining task-specific performance.
New method handles large reward variations in reinforcement learning.
problem Optimal policy not achievable with existing methods for non-deterministic processes.
method Introduces conjugated distributional operator for handling real returns.
result Guaranteed theoretical convergence for a wide class of transformations.
Automates data augmentation by learning from user-specified transformations.
problem Manual construction and tuning of complex data transformations for state-of-the-art results.
method Generative adversarial model over user-specified transformations trained on unlabeled data.
result Improves accuracy on CIFAR-10, ACE relation extraction, and medical imaging datasets.
Study shows computational and statistical gaps in Gaussian Single-Index Models.
problem Statistical and computational trade-offs in high-dimensional regression problems.
method Analysis of SQ and LDP frameworks, partial-trace algorithm.
result Computational algorithms require significantly more samples than information-theoretic limits.
Deep learning model estimates uncertainty in complex regression tasks.
problem Uncertainty quantification in probabilistic regression predictions.
method Combines statistical and deep learning transformation models using gradient descent.
result State-of-the-art performance on small datasets and complex image data.
Optimization framework for reconstructing missing mandible segments.
problem Missing mandible geometry in jaw reconstructive surgeries.
method Conditional variational autoencoder (CVAE) with weighted multi-target probabilistic solution.
result Statistically significant performance improvement over CVAE.
A new graphical method compares stochastic variables visually.
problem Comparing non-deterministic measurements visually.
method Cumulative distribution function dominance measure and quantile decomposition.
result Additional conclusions missed by other methods can be inferred.
The paper uses a novel framework to learn option prices by imitating principal investor behavior.
problem Challenges in modeling stock price changes and decision making in equity markets.
method Non-deterministic Markov decision process, Bayesian deep neural network, reinforcement learning.
result Optimal option prices learned through imitation of principal investor behavior.
This work improves understanding of dimension reduction algorithms and their probabilistic embeddings.
problem Improving theoretical understanding of non-linear dimension reduction algorithms.
method Analytical investigation of a generalized multidimensional scaling optimization problem.
result Probabilistic formulation of the problem leads to deterministic embeddings, contrary to standard implementations.
Improved autoencoder boosts sequence learning with less memory.
problem Training recurrent networks with high memory costs.
method Sparse Predictive Autoencoder (bRSM) with recurrent connections and boosting rule.
result Near optimal performance on stochastic sequence learning task.
Model forecasts motor vehicle collision rates with high accuracy.
problem Forecasting motor vehicle collision rates with high accuracy.
method Adopted Heston Stochastic Volatility model and extended it to account for seasonality and accelerated safety periods.
result Short-term forecasts show high accuracy (over 95%) and outperform existing models.
Improved tensor rank learning for CPD models using a generalized hyperbolic prior.
problem Inaccurate tensor rank determination leads to overfitting or underfitting in CPD models.
method Introduced a generalized hyperbolic prior for automatic tensor rank learning in probabilistic CPD models.
result Significantly improved performance in learning both low and high tensor ranks, even for low SNR cases.
Overview of integrable systems with symmetries, focusing on toric and semitoric systems.
problem Classifying and understanding integrable systems with symmetries.
method Using decorated polygons and controlled bifurcations in one-parameter families of systems.
result Construction of explicit semitoric systems with prescribed invariants.
New method to derive integrable systems from existing Lax systems.
problem Deriving new integrable systems from existing ones.
method Systematic method of deriving new integrable systems from a given one.
result Examples of new integrable systems derived, including the dispersionless Hirota equation, the general heavenly equation, and the web equations.
Learning to control linear systems is statistically hard, especially for underactuated systems.
problem Statistical difficulty of learning to control linear systems, especially underactuated ones.
method Utilized minimax lower bounds and structural assumptions to prove learning complexity can be exponential.
result Learning complexity can be at most exponential with the controllability index of the system.
Discrete-time systems can be characterized by simple flat coordinates and their shifts.
problem Characterizing flatness of discrete-time systems.
method Developed a map from flat coordinates and their shifts to system state and input, fulfilling system equations identically.
result Derived necessary conditions for a system to be flat, without requiring differential geometry methods.