MAC combines models without locking them, improving ensemble performance.
problem Improving ensemble learning performance with flexibility.
method Model agnostic combination technique that dynamically combines models.
result MAC outperforms classical methods and competitive to boosting.
SBT model uses randomized sharding and sub-models to improve Bayesian Additive Regression Trees.
problem Improving efficiency and accuracy of Bayesian Additive Regression Trees.
method Randomized sharding, sub-models, intersection tree structure, optimal design.
result Theoretical optimal weights and worst-case complexity of SBT model.
Predicting smartphone users activity using WiFi fingerprints has been a popular approach for indoor positioning in recent years. However, such a high dimensional time-series prediction problem can be very tricky to solve. To address this issue, we propose a novel deep learning model, the convolutional mixture density r…
We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with deep-supervision as proposed in \cite{xie2015holistically}, channel-wise nesting has…
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.
Fictitious play with reinforcement learning is a general and effective framework for zero-sum games. However, using the current deep neural network models, the implementation of fictitious play faces crucial challenges. Neural network model training employs gradient descent approaches to update all connection weights, …
Improves parallel deep model performance by restructuring and pruning.
problem Latency in parallel deep model execution due to interdependency among sub-models.
method Layer-wise model restructuring and pruning, using ℓ0 optimization and Munkres assignment algorithm. result Significantly improves efficiency of distributed inference in terms of communication and computational complexity.
With an eye toward understanding complexity control in deep learning, we study how infinitesimal regularization or gradient descent optimization lead to margin maximizing solutions in both homogeneous and non-homogeneous models, extending previous work that focused on infinitesimal regularization only in homogeneous mo…
A new framework for efficient Bayesian network inference.
problem High-dimensional Bayesian networks are hard to infer due to computational scaling.
method Directed convex subgraphs and minimal d-decomposition tree for decomposition, enabling parallel computation.
result The method reduces computational cost and enables parallel computation.
SuperNet speeds up neural network ensembling by training a single DNN for various phases.
problem High computational demand of ensembling large neural networks.
method Train a single DNN for multiple phases of training to represent various sub-models.
result SuperNet execution time comparable to single DNN training time plus coupling factors.
Hidden regular variation is a sub-model of multivariate regular variation and facilitates accurate estimation of joint tail probabilities. We generalize the model of hidden regular variation to what we call hidden domain of attraction. We exhibit examples that illustrate the need for a more general model and discuss de…
Multi-step-ahead time series prediction is one of the most challenging research topics in the field of time series modeling and prediction, and is continually under research. Recently, the multiple-input several multiple-outputs (MISMO) modeling strategy has been proposed as a promising alternative for multi-step-ahead…
Optimizes biomanufacturing processes with a new digital twin calibration method.
problem Lack of interpretability and sample efficiency in traditional DoE methods.
method Developed a computational approach to calibrate Bio-SoS digital twin model.
result Guides sample-efficient and interpretable DoEs by quantifying sub-model parameter estimation errors.
New methods for scalable inference in modular models with misspecified sub-models.
problem Model misspecification in multi-modular models complicates evidence combination.
method Variational methods for approximating Cut and SMI posteriors, and Variational Meta-Posterior.
result Feasibility of analysis with multiple cuts using a single set of variational parameters.
Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is typically sequentially processed and parameters are synchronously updated. Distr…
This paper introduces a deep learning ensemble forecasting model using Dirichlet process.
problem Forecasting with deep learning ensemble models.
method Infinite mixture model based on Dirichlet process, with decaying learning rate strategy.
result The ensemble model outperforms single benchmark models in prediction accuracy and stability.
Efficiently builds diverse sub-model ensembles for robust self-supervised learning.
problem Challenges in diversity and efficiency of deep ensembles for self-supervised representation learning.
method Ensemble of independent sub-networks with a new loss function for diversity.
result Significantly improves prediction reliability and model calibration.
We present a set of models relevant for predicting various aspects of intra-day trading volume for equities and showcase them as an ensemble that projects volume in unison. We introduce econometric methods for predicting total and remaining daily volume, intra-day volume profile (u-curve), close auction volume and spec…
This work falls within the context of predicting the value of a real function at some input locations given a limited number of observations of this function. The Kriging interpolation technique (or Gaussian process regression) is often considered to tackle such a problem but the method suffers from its computational b…
Large models collapse epistemic uncertainty, challenging traditional wisdom.
problem Epistemic uncertainty collapse in large models.
method Implicit ensembling and decomposition techniques.
result Larger models can collapse epistemic uncertainty, contrary to expectations.
New method for analyzing learning dynamics in singular models.
problem Challenges in analyzing learning of singular models with no one-to-one parameter space.
method Relative reparameterization technique to extract regular sub-models.
result Demonstrated differences in convergence behavior due to algorithmic and intrinsic aspects.
In this work we present Ludwig, a flexible, extensible and easy to use toolbox which allows users to train deep learning models and use them for obtaining predictions without writing code. Ludwig implements a novel approach to deep learning model building based on two main abstractions: data types and declarative confi…
Federated Learning is introduced to protect privacy by distributing training data into multiple parties. Each party trains its own model and a meta-model is constructed from the sub models. In this way the details of the data are not disclosed in between each party. In this paper we investigate the model interpretation…
This paper improves ASR performance by aligning frames more accurately.
problem Disagreement between teacher-student models in frame-level alignment.
method Introduces self-knowledge distillation (SKD) to guide frame-level alignment.
result Improves both resource efficiency and performance in ASR.
Unified model for market dynamics, linking price and order flow.
problem Modeling market dynamics and order flow in a unified framework.
method Markovian market model driven by a hidden Brownian efficient price, signal-driven and queue-reactive models.
result Stability of mid-price around efficient price at macroscopic scale, behavior as diffusion.
This paper tackles learning functions on manifolds using parallel distributed learning.
problem Learning real-valued functions on manifolds from input-output data pairs.
method Filtered hyperinterpolation and parallel distributed learning.
result Optimal approximation order for non-distributed case, and quantitative relations for distributed case.
This work proposes the Bregman-Tweedie classification model and analyzes the domain structure of the extended exponential function, an extension of the classic generalized exponential function with additional scaling parameter, and related high-level mathematical structures, such as the Bregman-Tweedie loss function an…
This study evaluates the robustness of transformation-based ensemble defense against evasion attacks.
problem Understanding the reasons behind the robustness improvement in transformation-based ensemble defense.
method Designing two adaptive attacks to evaluate transformation-based ensemble defense, conducting experiments to analyze robustness.
result The robustness improvement is mainly from irreversible transformations rather than the ensemble of models.
Recurrent neural networks have been widely used to generate millions of de novo molecules in a known chemical space. These deep generative models are typically setup with LSTM or GRU units and trained with canonical SMILEs. In this study, we introduce a new robust architecture, Generative Examination Networks GEN, base…
Estimates hybrid dynamical systems with polynomial expansions and Markovian switching.
problem Identifying hybrid dynamical systems with nonlinear autoregressive exogenous (NARX) components and Markovian switching.
method Probabilistic framework using Expectation Maximization for parameter estimation, including submodel coefficients, hidden state values, and transition probabilities. Disentangles mode classification and NARX regression tasks. Uses soft-labels and coordinate descent approach for parameter fitting.
result Demonstrated on a SMNARX problem with three nonlinear sub-models, achieving parsimonious models through l1-norm bridge estimation and hard-thresholding.
This paper proposes a representational model for grid cells. In this model, the 2D self-position of the agent is represented by a high-dimensional vector, and the 2D self-motion or displacement of the agent is represented by a matrix that transforms the vector. Each component of the vector is a unit or a cell. The mode…
RankNet forecasts car racing positions with improved accuracy and stability.
problem Forecasting rank positions in car racing, especially considering pit stops.
method Cause-effect decomposition in RankNet, incorporating probabilistic forecasting.
result RankNet outperforms baselines significantly, improving MAE by over 10%.
Image of an entity can be defined as a structured and dynamic representation which can be extracted from the opinions of a group of users or population. Automatic extraction of such an image has certain importance in political science and sociology related studies, e.g., when an extended inquiry from large-scale data i…
A new method for high-dimensional functional regression reduces multicollinearity and improves interpretability.
problem Multicollinearity, overfitting, and interpretability in high-dimensional functional linear models.
method Partition-based functional ridge regression framework.
result Improved numerical stability and enhanced interpretability without explicit variable selection.
Paper addresses online identification and clustering for mixed linear regression models.
problem Online identification and clustering of mixed linear regression models.
method Introduces two online identification algorithms based on the EM principle, proving global convergence without i.i.d. data assumptions.
result Global convergence of the proposed algorithms for mixed linear regression models.
A real-time federated neural architecture search approach reduces costs and improves performance.
problem High communication and computational demands in federated learning for large models.
method Evolutionary approach with double-sampling technique to optimize model performance and reduce costs.
result Effective real-time federated neural architecture search for deep models on edge devices.
The paper analyzes convergence rates of softmax gating in MoE models.
problem The effectiveness and scalability of machine learning models using MoE.
method Convergence analysis of parameter and expert estimation under MoE with softmax gating and its variants.
result Theoretical results show polynomially many data points are needed for strong identifiability conditions, while exponential points are required for linear experts.
Bayesian inference calibrates Hall thruster model uncertainty at varying pressures.
problem Quantifying uncertainty in a multi-component Hall thruster model at different facility pressures.
method Bayesian inference applied to calibrate and quantify prediction uncertainty in a coupled multi-component Hall thruster model.
result Model reduces predictive errors in thrust and discharge current by more than 50% compared to a previous model.
CoCoAFusE fuses expert predictions to model complex patterns with interpretability and uncertainty.
problem Modeling complex patterns with interpretability and uncertainty quantification.
method Competitive/Collaborative Fusion of Experts (CoCoAFusE) that fuses expert distributions in addition to mixing.
result CoCoAFusE avoids multimodality artifacts and provides tighter credible bounds on the response variable.
Paper addresses global convergence of MLR estimation under weak data conditions.
problem Learning mixed linear regression models with general data conditions.
method Two-step recursive identification algorithm using least squares and EM principles.
result Global convergence and optimal clustering performance established under general data conditions.
CNN improves stock price prediction accuracy.
problem Predicting future stock price movements.
method Hybrid approach combining machine learning and CNN.
result CNN-based model outperforms other models.
Automated method creates compact chemical models from detailed ones, reducing complexity and improving accuracy.
problem Creating accurate low-dimensional chemical kinetic models from detailed ones is time-consuming and requires expert knowledge.
method Machine Learned Optimisation of Chemical Kinetics (MLOCK) algorithm systematically perturbs sub-models to find optimal compact models.
result Compact models (15 species) retain ~87% fidelity to detailed models, outperforming previous methods.
TMLE improves IPM estimation for ecological population dynamics.
problem Estimating key demographic properties from IPM data.
method Targeted Maximum Likelihood Estimation (TMLE) for IPMs.
result Robust and efficient estimators for IPM properties.