Novel GLMMNet model tackles high-cardinality categorical features in actuarial applications.
problem Inadequate encoding methods for high-cardinality categorical features in actuarial data.
method Generalised Linear Mixed Model Neural Network (GLMMNet) integrating a generalised linear mixed model in a deep learning framework.
result GLMMNet often outperforms or performs comparably with entity embedded neural networks, providing transparency.
Noise-driven neural networks emerge modular structures, improving robustness and generalization.
problem Artificial neural networks struggle with modular solutions, leading to poor generalization and robustness.
method Inspired by brain's modular architecture, the study uses neural noise and nonlinear responses to drive the emergence of modular solutions.
result Noise-driven modularisation improves robustness and generalization in neural networks.
This paper explains double descent in linear neural networks, identifying new factors.
problem Understanding double descent in linear neural networks.
method Gradient flow derivation and necessary conditions for double descent.
result Singular values of input-output covariance matrix are important for double descent in two-layer models.
This review compares GAMs and neural networks on real-world tabular data.
problem Comparing the performance and characteristics of GAMs and neural networks in tabular data applications.
method Systematic review following PRISMA guidelines, extracting and analysing key attributes from 143 papers and 430 datasets.
result No consistent evidence of superiority for either GAMs or neural networks, with performance trade-offs depending on dataset characteristics.
Neural models improve GLMMs for complex data.
problem Nonlinear relationships in grouped data.
method Replaced linear function with neural networks.
result Improved performance on synthetic and real-world data.
New bounds for shallow neural networks with deterministic parameters.
problem Developing generalisation bounds for shallow neural networks.
method PAC-Bayesian theory applied to shallow neural networks with deterministic parameters.
result Empirical non-vacuous bounds for shallow neural networks trained with vanilla SGD.
Algorithm removes units and layers of neural networks without losing accuracy.
problem Deploying large neural networks under limited resources.
method Mixed-Integer Linear Programming (MILP) and L1 regularization.
result Lossless compression of neural networks is achieved.
Adding linear layers to ReLU networks favors functions with low mixed variation.
problem Understanding function space bias in overparameterized neural networks.
method Examined a family of networks with varying depths and same capacity but different representation costs, focusing on the effect of adding linear layers to the input side.
result Adding linear layers to shallow ReLU networks results in a bias towards functions with low mixed variation, which can be well approximated by single- or multi-index models.
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
Paper uses RL to optimize branching strategy in B&B algorithms.
problem Optimizing Branch and Bound algorithms for mixed integer linear programs.
method FMSTS, a Reinforcement Learning approach for variable selection.
result FMSTS outperforms commercial solvers in efficiency and generalization.
We extend neural networks with fractional and mixed activation functions for better function approximation.
problem Limitations in approximating higher-order smooth functions in complex spaces.
method Incorporating fractional exponents in activation functions and defining new density functions.
result Improved accuracy and broader applicability of neural network approximation theory.
Neural nets learn simple distributions first, then more complex ones.
problem Understanding how neural networks generalize from simple to complex functions.
method Stochastic gradient descent training, synthetic data, CIFAR10, ImageNet pre-training.
result Neural networks initially use lower-order statistics, then higher-order ones.
New method reveals why GNNs perform well on certain datasets.
problem Understanding why GNNs perform differently on similar datasets.
method Deriving exact generalization error for various GNN architectures.
result Benchmark datasets favor architectures that rely on graph structure.
NPE trains neural networks to approximate posterior distributions in SIR models from final outcome data.
problem Computational challenges in Bayesian inference for SIR models with final outcome data.
method Neural posterior estimation (NPE) using a logNormal posterior approximated by a neural network.
result NPE accurately recovers reference posteriors across various population sizes and transmission regimes.
Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a teacher-student setup, where one network, the student, is trained using stochastic gradient de…
New algorithms optimize neural networks with ReLU activations using sampling.
problem Optimizing trained neural networks with ReLU activations.
method Iterative algorithm and enhanced algorithm using sampling and neighborhood search.
result The methods reduce the initial MIP problem into smaller LP or MIP problems.
Graph neural networks generalize well under certain conditions, explained by learning theory.
problem Understanding why graph neural networks generalize well in transductive inference.
method Analysis of transductive Rademacher complexity to explain generalization properties of graph convolutional networks.
result Transductive Rademacher complexity can explain the generalization of graph convolutional networks for node classification in stochastic block models.
PAC-Bayes bound for stable RNNs in time-series data.
problem Bounding generalization gap for stable RNNs in time-series data.
method Derived a PAC-Bayes bound with stability constraints for discrete-time non-linear dynamical systems, including stable RNNs.
result The bound converges to zero as dataset size increases, and does not grow with RNN steps.
Study reveals phase transition in neural networks near interpolation.
problem Understanding generalization and learning transitions in neural networks.
method Effective theory for approximating Bayes-optimal generalisation error.
result Unveils a discontinuous phase transition between universal and specialisation phases.
Study on generalisation in random feature learning and hidden manifold models.
problem Generalisation in high-dimensional learning problems.
method Replica method from statistical physics for asymptotic generalisation performance.
result Closed-form expression for generalisation performance in various high-dimensional settings.
Proposes a new model for context-dependent decision-making.
problem Constant preference parameters in decision models are too rigid.
method Introduces Context-aware Bayesian mixed multinomial logit model using neural networks.
result Models context-dependent intra-respondent heterogeneity effectively.
ReLU networks trained with MILPs match deep learning accuracy.
problem Training deep neural networks efficiently.
method Iterative training with Mixed Integer Linear Programs (MILPs).
result ReLU networks can be trained with MILPs achieving similar accuracy to deep learning methods.
Method improves regression models using unlabeled data.
problem Improving predictive performance of regression models with limited labeled data.
method Mixed semi-supervised generalized-linear-regression with different mixing mechanisms.
result Integrating unlabeled data consistently improves predictive performance.
Directional and pairwise measurements are often used to model inter-relationships in a social network setting. The Mixed-Membership Stochastic Blockmodel (MMSB) was a seminal work in this area, and many of its capabilities were extended since then. In this paper, we propose the \emph{Dynamic Infinite Mixed-Membership s…
Spectral embedding is a procedure which can be used to obtain vector representations of the nodes of a graph. This paper proposes a generalisation of the latent position network model known as the random dot product graph, to allow interpretation of those vector representations as latent position estimates. The general…
In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) extensions to neural network structures that solve this problem and answer, as well as raise, questions about integrating structures for induct…
metabeta uses neural networks to speed up Bayesian mixed-effects regression.
problem Bayesian mixed-effects regression is computationally expensive.
method metabeta is a neural network model that pre-trains to estimate posterior distributions.
result metabeta achieves comparable performance to MCMC at a fraction of the time.
Study uses deep neural networks for inference in partially linear models with dependent data.
problem Inference in partially linear models with dependent data.
method First stage deep neural network (DNN) estimation followed by n \sqrt{n} n -consistent and asymptotically normal estimator. result The DNN-estimated finite dimensional parameter achieves n \sqrt{n} n -consistency and asymptotic normality. A new framework explains mixed models by propagating Shapley values.
problem Making complex models like neural networks and stacked models explainable for healthcare applications.
method DeepSHAP framework for layer-wise propagation of Shapley values.
result DeepSHAP enables attributions for mixed models and theoretically justifies attributions with respect to a background distribution.
A new SSL method improves medical image classification using global latent mixing.
problem Costly annotation of large-scale medical image data sets.
method Linear mixing of labeled and unlabeled data in both input and latent space.
result Improved performance in semi-supervised classification of thoracic disease and skin lesion.
Novel framework explains generalization in deep neural networks.
problem Understanding and improving generalization in deep neural networks.
method Topological Quantum Neural Networks as the semi-classical limit of Deep Neural Networks.
result Demonstrates that the perceptron, viewed as the semi-classical limit, achieves similar results to standard neural networks without training.
Characterizes a specific type of neural network for alternating group equivariance.
problem Understanding and characterizing neural networks with alternating group equivariance.
method Characterization of all possible A n A_n A n -equivariant neural networks using tensor powers of R n \mathbb{R}^{n} R n . result Found a basis of matrices for learnable, linear A n A_n A n -equivariant layer functions. New neural networks respect symmetries in symmetric tensors, improving efficiency and generalization.
problem Learning from symmetric tensors efficiently and respecting their inherent symmetries.
method Developed two characterizations of linear permutation equivariant functions between symmetric power spaces of R^n.
result These functions are highly data efficient compared to standard MLPs and generalize well to different sizes of symmetric tensors.
Study rare-event simulation for neural networks and random forests.
problem Safety evaluation and robustness quantification of machine learning models.
method Importance sampling scheme integrating large deviations and sequential mixed integer programming.
result Efficiency guarantees and numerical demonstrations for various neural network architectures.
This research quantifies neural networks using magnitude, a topological invariant.
problem Understanding the generalization capabilities of neural networks.
method Using a novel topological invariant called magnitude to study neural network representations.
result Magnitude dimension is theoretically connected to generalisation error and can predict it.
Computes indices of mixed order Dirac-type operators and related tensor fields.
problem Computing indices of mixed order Dirac-type operators and tensor fields.
method Using Hilbert complexes and differential operators of mixed order, computing indices with cohomology groups of tensor fields.
result Computation of indices for elasticity and biharmonic complexes.
Deep Gaussian processes (DGPs) are multi-layer hierarchical generalisations of Gaussian processes (GPs) and are formally equivalent to neural networks with multiple, infinitely wide hidden layers. DGPs are nonparametric probabilistic models and as such are arguably more flexible, have a greater capacity to generalise, …
We investigate the complexity of deep neural networks (DNN) that represent piecewise linear (PWL) functions. In particular, we study the number of linear regions, i.e. pieces, that a PWL function represented by a DNN can attain, both theoretically and empirically. We present (i) tighter upper and lower bounds for the m…
Improved machine learning for reservoir optimization problems.
problem Optimizing control in high-dimensional storage problems.
method Modified dynamic programming algorithm with neural networks for Bellman values and conditional cuts.
result Neural networks outperform classical feedforward networks in estimating Bellman values.
G-GLN extends GLNs to multiple regression and density modeling.
problem Learning features in deep neural networks.
method G-GLN uses a distributed and local credit assignment mechanism based on optimizing a convex objective.
result G-GLN achieves competitive or state-of-the-art performance on regression benchmarks.
Symmetry in neural networks affects generalization, as shown by CLT and RG transformations.
problem Improving generalization in neural networks by incorporating physical symmetries.
method Evaluation of symmetry constraints and expressivity in MLPs and GNNs using the CLT as a test case.
result Overly complex or overconstrained models generalize poorly, revealing a competition between symmetry constraints and expressivity.
New research limits how deep neural networks can be for certain functions.
problem Understanding the depth required for neural networks to represent specific functions.
method Mixed-integer optimization, polyhedral theory, tropical geometry.
result Neural networks with more than one layer are necessary to represent certain functions.
Many researchers implicitly assume that neural networks learn relations and generalise them to new unseen data. It has been shown recently, however, that the generalisation of feed-forward networks fails for identity relations.The proposed solution for this problem is to create an inductive bias with Differential Recti…
Study links neural network inductive bias, feature learning, and generalization on Boolean functions.
problem Understanding how neural networks learn and generalize on Boolean data.
method End-to-end analysis of depth-2 discrete fully connected networks and DNF formulas, using Monte Carlo learning.
result Predictable training dynamics and interpretable features emerge, linking inductive bias and generalization.
Probabilistic deep learning uses neural networks and models to handle uncertainty.
problem Handling uncertainty in deep learning models.
method Two approaches: probabilistic neural networks and deep probabilistic models.
result TensorFlow Probability library supports both approaches.
Graph neural networks improve solving linear optimization problems.
problem Improving the efficiency of solving linear optimization problems.
method Using graph neural networks to simulate standard interior-point methods for linear optimization problems.
result Graph neural networks can solve linear optimization problems close to optimality, often outperforming conventional solvers.
This paper compares methods for handling mixed-attribute data in GFMM neural networks.
problem Handling datasets with mixed features in GFMM neural networks.
method Three main methods: encoding, combining with other classifiers, and specific learning algorithms.
result Encoding methods and combining with decision trees improve GFMM models' performance.
We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However, enumerating these regions is prohibitive and the known analytical bounds are identical for…