New metric t-DCF improves ASVspoof challenge results by considering spoofing attack prior.
problem Shortcomings of EER metric in assessing CMs and ASV together.
method Developed t-DCF metric with 6 parameters to assess ASV and CMs together.
result t-DCF shows different rankings for higher spoofing attack priors.
SPRT-TANDEM improves sequential classification accuracy with fewer samples.
problem Efficiently classifying sequential data with high accuracy and low sampling cost.
method Deep neural network-based SPRT algorithm that estimates log-likelihood ratio of two hypotheses.
result SPRT-TANDEM achieves statistically significantly better classification accuracy than other classifiers with fewer samples.
Study introduces new financial ratios for better predicting company performance.
problem Lack of progress in predicting company performance and assessing financial risks.
method Developed new financial and macroeconomic ratios, supervised learning models, and Bayesian models.
result New proposed variables improve model accuracy and FNN performs best across multiple tasks.
STanHop predicts multivariate time series with memory-enhanced capabilities.
problem Predicting multivariate time series with memory-enhanced capabilities.
method Sparse Tandem Hopfield Network (STanHop) with two external memory modules.
result STanHop outperforms dense Hopfield models in memory retrieval error.
This study combines ASV and CM systems for better performance using reinforcement learning.
problem Improving the combined performance of ASV and CM systems for better t-DCF measure.
method Training ASV and CM components together using reinforcement learning.
result Training ASV and CM components together improves the performance of the combined system.
Improved protein identification in mass spectrometry data.
problem Expanding peptide scoring capabilities in tandem mass spectrometry.
method Deriving concave emission distributions for dynamic Bayesian networks.
result Efficiently learned scoring function outperforms state-of-the-art.
CEB enhances model resilience through simple entropy bottleneck.
problem Improving model robustness against adversarial attacks.
method Conditional Entropy Bottleneck (CEB) combined with data augmentation.
result CEB significantly boosts adversarial robustness on various benchmarks.
Generative model gradients enhance MS/MS peptide identification.
problem Improving peptide identification from MS/MS spectra.
method Leverage log-likelihood gradients of generative models in a kernel-based classifier.
result Fisher kernel outperforms other methods on MS/MS datasets.
The paper shows how data augmentation and regularization can enforce group equivariance in machine learning models.
problem Improving model performance by leveraging known symmetries in machine learning tasks.
method Training with data augmentation and regularization to enforce group equivariance.
result Equivariance of the trained model can be achieved through training on augmented data in tandem with regularization.
Liquid chromatography coupled with tandem mass spectrometry, also known as shotgun proteomics, is a widely-used high-throughput technology for identifying proteins in complex biological samples. Analysis of the tens of thousands of fragmentation spectra produced by a typical shotgun proteomics experiment begins by assi…
Unified approach for sequence design combining likelihood-free inference and black-box optimization.
problem Designing biological sequences efficiently and accurately.
method Unified probabilistic framework integrating likelihood-free inference and black-box optimization.
result Previous optimization methods can be adapted and new algorithms proposed within this framework.
AI can identify simple groups and match algebraic tables, even with limited training.
problem Can AI learn algebraic structures?
method Machine learning techniques (SVM, neural classifiers) applied to finite groups and rings.
result AI can correctly identify simple groups and match algebraic tables for small structures.
ISL algorithm tackles deep exploration efficiently.
problem Deep exploration in reinforcement learning.
method Derives ISL algorithm by augmenting RL objective with a novel regularization term.
result Empirically shows state-of-the-art performance on deep-exploration benchmarks.
This work improves Gaussian process regression for large, non-stationary data.
problem Scalability issues and performance degradation for non-stationary data.
method Combines variational free energy approximations with online expectation propagation and local splitting steps.
result Incremental adaptation to locality, heterogeneity, and non-stationarity in training data.
Data augmentation doesn't improve robustness, contrary to belief.
problem The effectiveness of data augmentation in improving model robustness is questioned.
method Taking a Domain Generalization viewpoint, the study examines the robustness of augmented representations.
result Augmented representations are not robust to distortions used during training.
Novel approach uses Gaussian processes to estimate conflict trends.
problem Estimating temporal and spatial patterns of violent conflict.
method Highly disaggregated conflict event data with Gaussian processes.
result Powerful conflict forecasts and insights into conflict dynamics.
New method connects curvature and Persistent Homology for networks.
problem Efficient computation of Persistent Homology for complex networks.
method Discrete Morse Theory, Bloch's extension, Forman-Ricci curvature.
result Efficient Persistent Homology scheme using curvature-based approach.
New research shows alternative linear connections can outperform identity shortcuts in deep networks.
problem Explaining the effectiveness of shortcut connections in deep neural networks.
method Used variations of the standard residual block with different types of linear connections to build image classification networks.
result Alternative linear connections can be more effective than identity shortcuts in deep networks.
Rewriting history improves RL algorithms for solving multiple tasks.
problem Improving sample efficiency in multi-task reinforcement learning.
method Introducing hindsight relabeling as inverse RL to generalize goal-relabeling techniques.
result Relabeling data using inverse RL accelerates learning in multi-task settings.
Study learns mixtures of smooth product distributions from samples.
problem Learning mixtures of non-parametric product distributions.
method Two-stage approach using identifiability properties of tensor decomposition and signal processing techniques.
result Recovery of component distributions under a smoothness condition.
A new method embeds sparse stochastic graphs into low dimensions.
problem Embedding large, sparse, stochastic graphs into low-dimensional spaces.
method Spaceland Embedding (SG-t-SNE) inspired by t-SNE, leveraging modern computing techniques.
result Effective embedding results on synthetic and real-world graphs.
Automates feature extraction from JSON data for machine learning.
problem Manual feature engineering for JSON data is laborious, lossy, and prone to bias.
method Automates feature extraction using Mill.jl and JsonGrinder.jl.
result Creates a differentiable machine learning model from raw JSON samples.
Generative networks improve by embedding data into a metric space.
problem Mode collapse in GANs.
method Metric embedding of data into l2 space, using Gaussian mixture model.
result GANs generate samples spanning most modes without mode collapse.
Adversarial learning approximates unknown quantum states on near-term quantum computers.
problem Approximating unknown quantum pure states on near-term quantum computers.
method Two parametrized circuits optimized adversarially, with resilient backpropagation and bipartite entanglement entropy.
result Resilient backpropagation algorithms perform well in optimizing the two circuits.
Kernel embeddings help estimate causal effects from observational data.
problem Estimating causal effects from observational data with confounding variables.
method Kernel embeddings in reproducing kernel Hilbert spaces (RKHS).
result Robust nonparametric framework for causal inference.
A new framework uses deep RL to aggregate expert advice for better portfolio management.
problem Improving portfolio management through expert advice and deep reinforcement learning.
method Convolutional networks for signal aggregation and historical price data, Proximal Policy Optimization algorithm.
result Our framework can achieve 90% of the best expert's profit on average.
Despite their attractiveness, popular perception is that techniques for nonparametric function approximation do not scale to streaming data due to an intractable growth in the amount of storage they require. To solve this problem in a memory-affordable way, we propose an online technique based on functional stochastic …
Large learning rates enhance model robustness and compressibility.
problem Achieving robustness and resource-efficiency in machine learning models.
method Identifying and utilizing large learning rates as a facilitator for robustness and compressibility.
result Large learning rates produce desirable representation properties and compare favorably to other methods.
New method uses multi-task learning to improve molecule representations.
problem Cost, bias, and data requirements in chemical representation generation.
method Intelligent task selection in deep multitask networks with transfer learning.
result Deep representations capture more expressive task-based information.
Extends knockoff filter for composite null hypotheses in variable selection.
problem Handling composite null hypotheses in variable selection.
method Developed two methods for composite inference with knockoffs: S-OLS and FRPP.
result Proposed heuristic variants of S-OLS outperforming BH procedure for composite nulls.
We discuss in this note applications of the Multidimensional Positive Definite Advection Transport Algorithm (MPDATA) to numerical solutions of partial differential equations arising from stochastic models in quantitative finance. In particular, we develop a framework for solving Black-Scholes-type equations by first t…
New theory shows interpretable models can outperform black-box models in decision-making systems.
problem The importance of interpretability in machine learning models.
method Characterized performance of two-node data fusion systems using distributed detection theory.
result A human with an interpretable classifier outperforms one with a black-box classifier.
Self-attention models benefit equally from width and depth, but beyond a certain point, depth becomes less efficient.
problem Understanding the optimal balance between depth and width in self-attention models.
method Theoretical predictions and empirical ablations on networks of varying depths and widths.
result An optimal width of 30K is recommended for a 1-Trillion parameter network, marking a significant width for self-attention models.
Protein structure prediction has been a grand challenge problem in the structure biology over the last few decades. Protein quality assessment plays a very important role in protein structure prediction. In the paper, we propose a new protein quality assessment method which can predict both local and global quality of …
Paper introduces active Bayesian method for assessing black-box classifiers efficiently.
problem Need to assess performance of black-box classifiers reliably with limited labels.
method Develops inference strategies and proposes active Bayesian framework for efficient instance selection.
result Significant gains in performance assessment with fewer labels compared to traditional methods.
HodgeRank method improves fairness in online peer assessments.
problem Bias and heterogeneity in peer assessment leading to unfair scoring.
method Reference ranking method using HodgeRank for online peer assessment.
result Objective scoring reference for instructors based on mathematics.
AI enhances refinery optimization by detecting data errors and improving decision-making.
problem Interpreting and applying LP solutions for refinery optimization is challenging due to simplifications and data errors.
method Transformed ECOD methodology, Anomaly Detection tools, and high-dimensional data analysis.
result Identifies data supply errors and reveals business opportunities in refinery scheduling and planning.
Study examines how different assessment formats affect student learning in a data communications course.
problem Understanding how various assessment formats impact student learning outcomes.
method Comparing student learning outcomes across multiple assessment formats in a core data communications course at George Mason University.
result Collective assessment formats enhance student knowledge demonstration.
New method assesses graph generators using graph classifiers.
problem Quantifying how well generative models create realistic graphs.
method Using graph classifiers to evaluate synthesized graphs against real ones.
result Inability of a classifier to distinguish real from synthetic graphs indicates poor model performance.
Paper explores physics-informed deep learning for system reliability assessment.
problem Limited study on deep learning for system reliability assessment.
method Physics-informed deep learning approach for system reliability assessment.
result Physics-informed deep learning can alleviate computational challenges and combine measurement data and mathematical models.
Locally sparse neural networks improve interpretability for biomedical tabular data.
problem Overfitting and lack of interpretability in neural networks for tabular biomedical data.
method Locally sparse neural network with a gating network to select relevant features.
result The method outperforms state-of-the-art models in synthetic and real-world biomedical datasets.
chemmodlab simplifies fitting and assessing machine learning models in cheminformatics.
problem Comparing the utility of new machine learning models in cheminformatics.
method Streamlines model fitting and assessment pipeline, using k-fold cross-validation and multiplicity adjustments.
result Ease of presenting statistically significant performance differences among models.
Bayesian networks improve product risk assessment by handling uncertainty and causality.
problem Limited handling of uncertainty and inability to incorporate causal explanations in existing methods.
method Bayesian Networks (BNs) for improved systematic product risk assessment.
result BN approach provides more powerful and flexible risk assessments.
Enhances early risk assessments for pediatric outcomes using contrastive learning.
problem Improving risk assessments in early stages of pediatric development.
method Contrastive multi-modal framework that treats each time window as a distinct modality, training on all available data.
result Consistent improvements in early-stage risk assessments validated on real-world tasks.
The paper improves regret lower bounds for communicating MDPs.
problem Regret lower bounds for communicating MDPs.
method Lower bound proof and optimization problem formulation.
result Regret lower bound becomes significantly more complex in communicating MDPs.
DETOX improves distributed training resilience with redundancy and robust aggregation.
problem Byzantine node failures in distributed training.
method Combines redundancy and robust aggregation methods.
result Substantial increase in robustness with nearly linear runtime.
Improved assessment of knee osteoarthritis using geodesic B-score.
problem Need for automatic, reader-independent measures of osteoarthritis clinical outcomes.
method Derive a geodesic B-score for Riemannian shape spaces, develop efficient algorithm for large shape populations.
result Geodesic B-score exhibits improved discrimination ability over Euclidean B-score.
Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.
problem High costs in GPU-days for training and fine-tuning language models.
method Memoization-aware Bayesian Optimization (EEIPU) algorithm in tandem with pipeline caching.
result EEIPU produces 103% more hyperparameter candidates and 108% more validation metric improvement.