The paper introduces COAR to estimate component attributions and enable model editing.
problem Understanding how ML models transform inputs into predictions.
method Component modeling and COAR algorithm for estimating component attributions.
result COAR enables model editing across various tasks.
System learns to combine multiple model components for personalized text generation.
problem Adapting and biasing language models for personal preferences.
method Combines model-defined components, learns activation and probability combination from unlabeled text.
result Directly generates text with personalized components from unlabeled data.
A big challenge in environmental monitoring is the spatiotemporal variation of the phenomena to be observed. To enable persistent sensing and estimation in such a setting, it is beneficial to have a time-varying underlying environmental model. Here we present a planning and learning method that enables an autonomous ma…
We present a new model DrNET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a stationary part and a temporally varying component. The disentangled representation can …
A model retains learned knowledge for longer by adding a plastic component to neural networks.
problem Catastrophic forgetting in neural networks when learning new tasks.
method Differentiable Hebbian Consolidation model with a DHP Softmax layer.
result Reduces forgetting in benchmarks like Permuted MNIST and Vision Datasets Mixture.
Generative model identifies temporal count data components with regime-dependent contributions.
problem Modeling temporal count data with regime-dependent dynamics.
method Generative framework combining regime-adaptive dynamics with Poisson log-normal emissions.
result Established identifiability of the model and revealed co-variation patterns and regime shifts.
The paper presents a method to compute trusted confidence bounds for LECs in CPS.
problem Non-transparent predictions of LECs make CPS safety challenging.
method Inductive Conformal Prediction (ICP) and Triplet Network architecture.
result Efficient real-time computation of trusted confidence bounds.
The paper detects adversarial examples in LECs for regression in CPS using variational autoencoder.
problem Detecting adversarial examples in learning-enabled cyber-physical systems (CPS).
method Inductive conformal prediction using a variational autoencoder regression model.
result The method effectively detects adversarial examples with a short delay in an emergency braking system simulation.
Gradient descent with growing learning rate enables learning non-linear features in neural networks.
problem Learning non-linear features in two-layer neural networks.
method Using gradient descent with a learning rate that grows with the sample size.
result Multiple rank-one components emerge, each corresponding to a specific polynomial feature.
Proposes FMPCA for federated tensor data dimensionality reduction.
problem Integration of MPCA into federated learning.
method Federated Multilinear Principal Component Analysis (FMPCA).
result FMPCA preserves performance of traditional MPCA in federated learning.
Study develops machine learning model to predict component movement during reflow in SMT.
problem Inaccurate self-alignment of components during reflow process in SMT leads to defects.
method Experimental data analysis followed by advanced machine learning models (SVR, NN, RFR) to predict component shift in x, y, and rotational directions.
result Random forest regression (RFR) model predicts component shift with high accuracy and low error.
A methodology for resilience analysis of Capsule Networks under approximation errors.
problem Resilience of Capsule Networks under approximation errors.
method Modeling and analyzing approximation errors in Capsule Networks' inference.
result Capsule Networks are more resilient to errors during dynamic routing than other stages.
Gradient Boosted Mixed Models estimate mean and variance components for clustered data.
problem Limited flexibility in linear mixed models for complex settings.
method Gradient Boosting extended to mixed models with likelihood-based gradients and flexible base learners.
result Accurate recovery of variance components and improved predictive accuracy.
Federated learning improves SPCA for sparse components.
problem Data privacy and sharing constraints in machine learning.
method Federated learning framework applied to SPCA with L1 regularization and smoothing.
result Federated SPCA achieves sparse component loadings with improved interpretability.
Despite a lack of theoretical understanding, deep neural networks have achieved unparalleled performance in a wide range of applications. On the other hand, shallow representation learning with component analysis is associated with rich intuition and theory, but smaller capacity often limits its usefulness. To bridge t…
Real-time detection of out-of-distribution data in CPS control systems.
problem Detecting out-of-distribution data in CPS control systems for safety.
method Inductive conformal prediction and anomaly detection using variational autoencoders and deep support vector data description.
result Efficient real-time detection with low false alarm rates and comparable execution time.
GLAMOUR learns from macromolecules, overcoming diversity challenges.
problem Challenges in machine learning with macromolecules due to their vast diversity.
method Developed GLAMOUR, a framework for chemistry-informed graph representation of macromolecules.
result Quantifies structural similarity and enables supervised learning for macromolecules.
Principal component regression (PCR) is a two-stage procedure that selects some principal components and then constructs a regression model regarding them as new explanatory variables. Note that the principal components are obtained from only explanatory variables and not considered with the response variable. To addre…
Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and ca…
AlphaZero's reward function is replaced with a total ordering, enabling self-play without balancing.
problem Learning optimal play in games without explicit reward balancing.
method Modified AlphaZero algorithm using only a total ordering of game outcomes.
result Comparable optimal play learned in a similar time frame without balancing.
Meta-materials simulation sped up with energy surrogates.
problem Challenging simulation of complex meta-materials due to high-fidelity PDEs.
method Learned component-level surrogates using neural networks to model stored potential energy.
result Surrogates enable accurate macroscopic behavior simulation without full structure simulation.
In this paper, we introduce a novel concept for learning of the parameters in a neural network. Our idea is grounded on modeling a learning problem that addresses a trade-off between (i) satisfying local objectives at each node and (ii) achieving desired data propagation through the network under (iii) local propagatio…
Paper presents a modular RL framework for Forex trading, addressing limitations of prior studies.
problem Challenges in applying RL to Forex trading, including unrealistic environments, simplified rewards, and restricted action spaces.
method Integrates three components: a friction-aware execution engine, a decomposable reward architecture, and a discrete action interface.
result Empirical evaluation shows strong non-monotonic reward interactions and optimal Sharpe ratio with the full reward configuration.
We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data. While metric learning enables a problem-adapted representation of data, the majority of methods has been proposed for vectorial data onl…
A new method improves posterior approximation for complex distributions.
problem Difficulty in capturing multimodal and heavy-tailed posteriors with standard normalizing flows.
method StiCTAF: stick-breaking mixture base with component-wise tail adaptation.
result Improved tail recovery and better mode coverage compared to benchmarks.
Improves scalability and efficiency of mixture models in black-box variational inference.
problem Scaling mixture models in black-box variational inference leads to high parameter and time costs.
method Introduces MISVAE for amortized mixture parameter space and new ELBO estimators.
result Achieves superior estimation performance with fewer parameters and shorter inference time.
Enhances mixture models with classifier-defined weights.
problem Density evaluation and sampling in mixture models.
method Introduces Classifier Weighted Mixtures (CWM) with functional weights.
result Improves expressivity in variational estimation without increasing complexity.
Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that l…
Slot Attention extracts object-centric representations from images.
problem Learning distributed representations that don't capture natural scene composition.
method Slot Attention module interfaces with CNN outputs to produce task-dependent abstract slots.
result Slot Attention enables generalization to unseen compositions.
A novel approach is put forth that utilizes data similarity, quantified on a graph, to improve upon the reconstruction performance of principal component analysis. The tasks of data dimensionality reduction and reconstruction are formulated as graph filtering operations, that enable the exploitation of data node connec…
Bayesian-TPNN improves ANOVA-TPNN for detecting higher-order components.
problem Difficulty in incorporating higher-order components in ANOVA-TPNN due to computational and memory constraints.
method Bayesian inference procedure for functional ANOVA model with TPNN basis functions.
result Bayesian-TPNN detects higher-order components with reduced computational cost.
Novel F2NARX model improves surrogate modeling for stochastic dynamical systems.
problem Challenges in constructing accurate and efficient surrogate models for stochastic dynamical systems.
method Function-on-Function Nonlinear AutoRegressive model with eXogenous inputs (F2NARX) combining PCA and Gaussian process regression.
result F2NARX outperforms state-of-the-art NARX models in efficiency and accuracy.
Python's tools drive machine learning advancements across industries.
problem Processing and analyzing large data sets for insights.
method Advancements in deep learning, classical ML, and GPU computing.
result Python's dominance in scientific computing boosts machine learning adoption.
Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring all-important …
A novel online framework for analyzing multidimensional functional data.
problem Analysis of multidimensional functional data streams poses significant challenges.
method Online functional principal component analysis using tensor product splines on a Stiefel manifold with Riemannian stochastic gradient descent.
result Efficient and scalable modeling of multidimensional functional data.
A hybrid loss framework improves time series forecasting by balancing global and component errors.
problem Current time series methods may prioritize less significant sub-series, leading to forecasting bias.
method Proposes a hybrid loss framework combining global and component losses, dynamically adjusting weights.
result Improves time series forecasting performance by 0.5-2% on average.
Real world systems typically feature a variety of different dependency types and topologies that complicate model selection for probabilistic graphical models. We introduce the ensemble-of-forests model, a generalization of the ensemble-of-trees model. Our model enables structure learning of Markov random fields (MRF) …
A new PCR method using SVD with sparse regularization.
problem Lack of response variable information in traditional PCR.
method One-stage SVD approach with two loss functions and sparse regularization.
result Obtains principal component loadings with response variable information.
The paper uses spectral flow on SPD matrices to analyze multimodal data.
problem Analyzing data from multiple sensors with shared and unique sources.
method Combines manifold learning with Riemannian geometry of SPD matrices.
result Spectral analysis of kernels on SPD manifold reveals common and unique components.
Bayesian model uses simple functions to forecast macroeconomic data.
problem Forecasting large datasets in macroeconomics with complex nonlinear relationships.
method Sum of simple two-component location mixtures, logistic function threshold, conjugate priors.
result Accurate point and density forecasts in US macroeconomic aggregates.
R-PCA extends PCA to Riemannian manifolds for structured data.
problem Applying PCA to data on Riemannian manifolds without vector space operations.
method Adapting PCA to Riemannian manifolds by equipping data with local metrics.
result Unified approach for dimensionality reduction and statistical analysis on manifolds.
A new unsupervised contrastive learning framework improves time series representation learning.
problem Lack of labeled data in time series data.
method Proposes an unsupervised contrastive learning framework using a novel contrastive loss and data augmentation.
result Framework outperforms other approaches on univariate and multivariate time series, and benefits transfer learning.
MILCCI integrates labels across categories for better understanding of multi-trial data.
problem Understanding how labels encode multi-trial observations and disentangling their effects.
method Sparse per-trial decomposition leveraging label similarities within each category.
result MILCCI identifies interpretable components and integrates label information.
Deep RL trains a robust humanoid push-recovery policy.
problem Training robust humanoid push-recovery policies.
method Model-free Deep Reinforcement Learning.
result Policy learns robust behaviors across the entire body.
New method compresses non-Gaussian distributions exponentially.
problem Efficiently representing and computing non-Gaussian probability distributions.
method Tensor-Network Fourier Methods using QTT representation.
result Exponential compression of non-Gaussian distributions.
This paper tackles sequential distribution shifts in representation learning.
problem Learning meaningful representations in a sequence of distribution shifts.
method Nonlinear Independent Component Analysis (ICA) framework for continual causal representation learning.
result The method achieves performance comparable to joint training on multiple offline distributions and shows no benefit from the incoming new distribution on all latent variables.
A new neural network reduces high-dimensional time-series data for faster classification.
problem Classifying high-dimensional time-series patterns efficiently.
method Developed a time-series discriminant component network (TSDCN) using TSDCA for dimensionality reduction and classification.
result The TSDCN achieves high-accuracy classification and reduces training time.
A new method for decision-focused learning reduces computational cost.
problem Efficiently solving combinatorial problems with uncertain parameters.
method Reframed as cost-sensitive multi-output regression, with novel loss components.
result Comparable downstream task quality with reduced computational cost.