Neural Thompson Sampling uses deep neural networks for contextual bandit problems.
problem Solving contextual multi-armed bandit problems.
method Adapts deep neural networks for exploration and exploitation in a novel posterior distribution.
result Guaranteed cumulative regret of O ( T 1 / 2 ) \mathcal{O}(T^{1/2}) O ( T 1/2 ) for bounded reward functions. Langevin algorithms improve training of very deep neural networks, especially for image classification.
problem Training very deep neural networks is challenging due to increased non-linearity and the risk of getting stuck in local minima.
method Comparison of Langevin and non-Langevin algorithms for training deep neural networks, introduction of Layer Langevin algorithm.
result Langevin algorithms, especially Layer Langevin, lead to significant improvements in training deep neural networks, particularly for image classification tasks.
Neural networks mimic algorithms to solve complex problems.
problem Current machine learning methods struggle with generalisation and efficiency.
method Representing algorithms in a continuous space and adapting them to real-world problems.
result Neural networks can execute classical algorithms more efficiently.
Graph Neural Networks align with dynamic programming, improving algorithmic reasoning.
problem Demonstrate and quantify alignment between GNNs and dynamic programming.
method Category theory and abstract algebra methods to expose intricate connection.
result Showed GNNs align with dynamic programming beyond individual algorithms.
Generalist neural learner can execute multiple algorithms.
problem Building models that can execute multiple algorithms.
method Single graph neural network processor, incorporating knowledge from specialist models.
result Generalist learner can execute multiple algorithms with improved performance.
Learning to Optimize is a recently proposed framework for learning optimization algorithms using reinforcement learning. In this paper, we explore learning an optimization algorithm for training shallow neural nets. Such high-dimensional stochastic optimization problems present interesting challenges for existing reinf…
We propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified…
Langevin algorithms enhance training of deep neural networks for stochastic control problems.
problem Training acceleration for deep neural networks in stochastic control problems.
method Application of Langevin algorithms to minimize the loss of deep neural networks in stochastic control problems.
result Langevin algorithms improve training on various stochastic control problems.
Neural- σ 2 σ^2 σ 2 -LinearUCB improves regret in neural contextual bandits.
problem Balancing exploration and exploitation in neural contextual bandits.
method Proposes a variance-aware neural UCB algorithm using neural representations and an upper bound of reward noise variance.
result Oracle and practical versions of Neural- σ 2 σ^2 σ 2 -LinearUCB achieve better regret guarantees and performance. Paper uses AI to predict stock market volatility with neural networks and genetic algorithms.
problem Traditional methods for predicting stock market volatility have high errors.
method Back-propagation neural network and genetic algorithm integrated model.
result The model predicts future volatility with low errors and high accuracy.
Optimization algorithms help overparameterized neural networks achieve high performance.
problem Understanding the convergence of optimization algorithms on overparameterized neural networks.
method Analyzing a broad class of optimization algorithms using dynamical systems and finite over-parameterized neural networks with ReLU activation.
result The Heavy Ball method converges to global minimum at a linear rate, while NAG converges sublinearly.
We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially overlapping) patches, including commonly used structures for computer vision tasks. Our a…
NAS helps find best neural network designs.
problem Designing optimal neural network architectures.
method Optimization algorithms and search spaces.
result Introduction to major advances in NAS for CNNs.
New neural network improves audio classification accuracy.
problem Challenging audio classification problem in pattern recognition.
method Introduces a Classifier-Attention-Based Convolutional Neural Network (CAB-CNN) with an attention mechanism to reduce classifier complexity.
result Significantly improves audio classification performance, achieving more than 10% improvements.
Neural execution solves complex graph problems like bipartite matching.
problem Solving complex graph algorithms like maximum bipartite matching.
method Reduces bipartite matching to a flow problem and uses Ford-Fulkerson for maximum flow.
result Neural network achieves optimal matching almost 100% of the time.
Genetic algorithms optimize neural networks for cosmological data analysis.
problem Inaccurate results from neural networks due to poor hyperparameter selection.
method Used genetic algorithms to optimize hyperparameters of neural networks.
result Genetic algorithms improve neural network performance in cosmological data analysis.
Proposes a copula-based method to interpret neural networks.
problem Neural networks lack interpretability due to ambiguity in decision-making.
method Uses pair copula correlation coefficients to reveal feature importance and decision paths.
result Consistent results with Random Forest's feature importance values.
We provide a proof of backpropagation algorithm in matrix notation.
problem The lack of a full induction proof of backpropagation algorithm in matrix notation.
method We provide a full induction proof of the BP algorithm in matrix notation, situating it in the framework of matrix differential calculus.
result We prove the validity of the backpropagation algorithm in inductive form.
GOLS-I automatically determines learning rates for various neural network training algorithms.
problem Adapting learning rates in stochastic training algorithms for neural networks.
method Gradient-Only Line Search (GOLS-I) for automatically setting learning rates.
result GOLS-I learning rate schedules are competitive with manually tuned rates across multiple algorithms, architectures, datasets, and loss functions.
New algorithm for efficient prediction intervals in neural networks.
problem Challenges in estimating uncertainty in neural network predictions.
method Applies matrix sketching to approximate Jacobian matrix for efficient uncertainty estimation.
result Produces approximate prediction intervals with competitive performance.
Researchers analyze and improve latent space in NAR models.
problem Latent space resolution and range issues in NAR models.
method Detailed analysis of GNN latent space structure, proposing and testing solutions.
result Improvements in majority of algorithms on CLRS-30 benchmark.
New learning algorithm mimics biological neural networks.
problem Biologically implausible backpropagation for directed neural networks.
method Introduces new neuronal dynamics and learning rule for arbitrary architectures, sparsity-inducing pruning method, and dynamical-systems characterization.
result Prunes irrelevant connections and improves learning efficiency.
A new faster neural network training method using backprojection.
problem Training feedforward neural networks more efficiently.
method Projection and reconstruction at each layer to force projected data and reconstructed labels to be similar.
result The proposed method is faster than backpropagation and gives insights into networks.
A new algorithm learns from raw feature vectors using deep neural networks and UCB for exploration.
problem Learning from raw feature vectors with unknown reward functions.
method Deep representation learning followed by UCB exploration in the last layer.
result Achieves i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) finite-time regret. SMGD trains low-bit neural networks with memory constraints.
problem Training large neural networks with limited memory.
method Stochastic Markov Gradient Descent (SMGD).
result Encouraging numerical results and theoretical guarantees.
Neural model with parameterized algorithms improves graph CO problem solving.
problem Solving NP-hard graph combinatorial optimization problems efficiently and accurately.
method Combining neural models and parameterized algorithms to identify and handle hard and easy parts of CO instances.
result Framework produces superior solution quality and out-of-distribution generalization.
Novel neural network solves PDEs with multi-scale resolution.
problem Solving time-dependent PDEs with varying spatial and temporal scales.
method Multi-scale message passing neural network with temporal and spatial gating modules.
result Outperforms baselines on PDEs with diverse scales.
Study shows accuracy of neural networks depends more on error location than percentage of error.
problem Effect of noise on accuracy in incremental learning neural networks.
method Empirical study using Perceptron, Feed Forward Neural Network, and Radial Basis Function Neural Network.
result Accuracy of neural networks is more dependent on error location than the percentage of error.
Combines MCTS and neural networks for efficient multi-period financial planning.
problem Solving multi-period financial planning models with high transaction costs and regime switching.
method Integrates Monte Carlo Tree Search with deep neural networks, using UTC and lookup search.
result Combined approach outperforms individual methods, solving complex models.
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.
New algorithm improves stability and efficiency of neural network training.
problem Stability and efficiency issues in adaptive optimization for neural networks.
method Polygonal approximations for SDEs with monotone coefficients, providing stability and addressing vanishing gradients.
result TheoPouLa algorithm shows superior performance over popular adaptive optimizers.
In this paper, we briefly review the basic scheme of the pseudoinverse learning (PIL) algorithm and present some discussions on the PIL, as well as its variants. The PIL algorithm, first presented in 1995, is a non-gradient descent and non-iterative learning algorithm for multi-layer neural networks and has several adv…
NPENAS improves neural architecture search efficiency and accuracy.
problem Efficient and accurate neural architecture search (NAS) for minimizing search costs.
method Proposes NPENAS, a neural predictor guided evolutionary algorithm that enhances exploration ability of evolutionary algorithms.
result NPENAS-BO and NPENAS-NP outperform existing NAS algorithms on NASBench-201, NASBench-101, and DARTS.
New algorithms reduce communication in GNN training.
problem Higher communication costs in GNNs due to sparse connectivity.
method Parallel algorithms for sparse-dense matrix multiplication.
result Asymptotic reduction in communication compared to previous methods.
Physics-informed neural networks simulate radiative transfer efficiently.
problem Simulating radiative transfer accurately and efficiently.
method Physics-informed neural networks trained to minimize radiative transfer equations.
result PINNs provide an easy-to-implement, robust, and accurate method for radiative transfer simulation.
Proposes a new model for community detection using neural priors.
problem Community detection in graphs with node attributes.
method Neural-prior stochastic block model with belief propagation and approximate message passing algorithm.
result Identifies phase transitions and algorithmically hard regions for community detection.
NNs can learn efficient algorithms for certain problems.
problem Learning efficient algorithms for specific problems.
method Recurrent Convolutional Neural Networks (RCNNs) that learn efficiently.
result RCNNs can learn as well as efficient algorithms described by a constant-sized program.
A new algorithm for learning shallow neural networks with infinite width.
problem Learning shallow over-parameterized neural networks.
method Sinkhorn proximal algorithm approximating mean field learning dynamics.
result The algorithm performs gradient descent of the free energy associated with the risk functional.
New algorithms for neural bandits learn from context and arm features.
problem Learning from context and arm features in combinatorial bandit problems.
method Proposed algorithms CN-UCB and CN-TS using deep neural networks.
result Achieved regret guarantees for the first time in combinatorial neural bandits.
Study shows how steepest descent algorithms' geometric margin increases during training.
problem Understanding implicit bias in steepest descent algorithms for neural networks.
method Analysis of steepest descent algorithms with infinitesimal learning rates in homogeneous neural networks.
result Limit points of training trajectories correspond to KKT points of margin-maximization problems.
While neural networks have achieved vastly enhanced performance over traditional iterative methods in many cases, they are generally empirically designed and the underlying structures are difficult to interpret. The algorithm unrolling approach has helped connect iterative algorithms to neural network architectures. Ho…
Bayesian method improves neural net convergence for character recognition.
problem Improving convergence rate of neural network training algorithms.
method Customization of Kalman filter into Bayesian statistics for initialization of weights.
result Improved convergence rate for backpropagation training algorithm.
Algorithm removes spurious concepts from neural network representations without harming task performance.
problem Spurious correlations hinder neural network out-of-distribution generalization.
method Iterative algorithm that identifies two orthogonal subspaces in neural network representation.
result Algorithm outperforms existing methods on computer vision and natural language processing benchmarks.
NHC learns scalable algorithmic solutions from diverse tasks.
problem Neural networks struggle to learn algorithmic strategies.
method Memory-augmented network with abstraction mechanism and evolutionary training.
result Reliable learning of robust and scalable algorithmic solutions.
New IRL algorithm identifies optimal reward and policy from expert demonstrations.
problem Understanding reward functions from expert demonstrations with neural networks.
method Two-timescale single-loop IRL algorithm for neural network parameterized rewards.
result First IRL algorithm with non-asymptotic convergence guarantee and global optimality in neural network settings.
Optimizes graph neural networks using natural gradient descent.
problem Improving efficiency and performance of graph neural networks.
method Employing natural gradient descent to optimize graph neural networks.
result Natural gradient optimization leads to superior performance compared to existing methods.
Model change points in time-series data with neural SDEs and variational autoencoders.
problem Modeling change points in time-series data with neural stochastic differential equations.
method Proposes a novel model formulation and training procedure based on the variational autoencoder framework, alternating between updating neural SDE parameters and change points.
result Demonstrates the expressive power of the proposed model in modeling both classical parametric SDEs and real datasets with distribution shifts.
New algorithm explains neural network extrema for better model generalization.
problem Understanding and improving neural network generalization.
method Dynamic extremum mapping and solving linear equations.
result Number of extrema correlates with model parameters, and new algorithm simplifies gradient issues.