Polynomial-time convex optimization for CNNs with ReLU activations.
problem Training Convolutional Neural Networks (CNNs) with ReLU activations.
method Developed a convex analytic framework using semi-infinite duality to formulate equivalent convex optimization problems for CNN architectures.
result Proved that two-layer CNNs can be globally optimized via an ℓ 2 \ell_2 ℓ 2 norm regularized convex program. Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.
problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.
Three-layer networks learn more complex features than two-layer networks.
problem Understanding feature learning in deep neural networks.
method Analysis of three-layer neural networks trained with gradient descent.
result Three-layer networks can learn functions that two-layer networks cannot.
New proof shows neural networks can represent all multivariate functions.
problem Representing all multivariate functions with neural networks.
method Proved that three-layer neural networks can represent both continuous and discontinuous functions.
result Three-layer neural networks can represent all multivariate functions, including discontinuous ones.
Three-layer neural networks learn hierarchical polynomial functions efficiently.
problem Learning hierarchical polynomial functions with three-layer neural networks.
method Layerwise gradient descent on square loss, focusing on feature learning.
result Achieves optimal sample complexity for learning hierarchical polynomials.
Analytical solution found for a three-layer network with a specific activation function.
problem Understanding the power of depth in neural networks.
method Found analytical solutions for a three-layer network with a matrix exponential activation function.
result Analytical solutions for equations involving a three-layer network with a matrix exponential activation function.
Global convergence proved for three-layer neural networks in mean field regime.
problem Optimization efficiency of multilayer neural networks in the mean field regime.
method Developed a rigorous framework for mean field limit of three-layer networks using stochastic gradient descent and neuronal embedding.
result Global convergence guarantee for unregularized feedforward three-layer networks in the mean field regime.
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a meta-layer that decides the intermediate goals, an action-layer that selects local…
The study analyzes a three-layer neural network's training dynamics using a functional-space mean-field theory.
problem Understanding the training dynamics of partially-trained three-layer neural networks.
method Generalized mean-field theory to functional spaces, proving convergence and feature learning.
result The training loss of the model decays to zero at a linear rate in the L 2 L_2 L 2 regression setting. Three-layer networks learn complex hierarchical polynomials of multiple nonlinear features.
problem Understanding how neural networks learn hierarchical features of multiple nonlinear inputs.
method Examine a broad class of functions using three-layer neural networks, showing complete recovery and efficient learning.
result Three-layer neural networks trained via gradient descent can learn hierarchical polynomials of multiple nonlinear features efficiently.
Deep ReLU networks can be simplified to a three-layer model.
problem Understanding the behavior of deep neural networks.
method Constructive proof and algorithm to transform deep networks into shallow ones.
result Deep ReLU networks can be represented by a simpler three-layer structure.
The paper extends mean field results to three-layer neural networks using SGD.
problem Understanding the dynamics of training three-layer neural networks with SGD.
method Extending mean field results from two-layer networks to three-layer networks with two hidden layers, using non-linear partial differential equations.
result The distributions of weights in the two hidden layers are independent.
This paper extends stability and generalization analysis of GD for multi-layer NNs.
problem Understanding the generalization of multi-layer neural networks trained by GD.
method Comprehensive stability and generalization analysis of GD for multi-layer NNs, focusing on two-layer and three-layer networks.
result Derives excess risk rates of O ( 1 / n ) O(1/\sqrt{n}) O ( 1/ n ) for GD in two-layer and three-layer NNs under specific conditions. The paper demonstrates the use of the fully convolutional neural network for glioma segmentation on the BraTS 2019 dataset. Three-layers deep encoder-decoder architecture is used along with dense connection at encoder part to propagate the information from coarse layer to deep layers. This architecture is used to train…
Study analyzes error in neural network solving PDEs, providing convergence and error bounds.
problem Error analysis of neural network solving PDEs.
method Three-layer tanh neural network with projected gradient descent (PGD).
result Comprehensive error analysis including approximation, generalization, and optimization errors.
Sleep disorders are implicated in a growing number of health problems. In this paper, we present a signal-processing/machine learning approach to detecting arousals in the multi-channel polysomnographic recordings of the Physionet/CinC Challenge2018 dataset. Methods: Our network architecture consists of two components.…
This work explains neural collapse in shallow neural networks and its impact on generalization.
problem Understanding neural collapse in shallow neural networks and its effect on generalization.
method Analysis of two and three-layer ReLU neural networks, focusing on data dimension, sample size, and signal-to-noise ratio.
result Neural collapse occurs in shallow ReLU networks under certain conditions related to data properties and network architecture.
Deep learning can learn compositional functions more efficiently by breaking them into stages.
problem Understanding why deep learning performs better than shallow models in learning compositional functions.
method Analyzed learnability of compositional target functions using a three-layer fitting model trained with layer-wise spectral estimators.
result Learning compositional functions can be simplified by breaking them into stages, reducing the complexity of the learning problem.
New algorithm interpolates data with neural nets, independent of sample size.
problem Understanding neural networks' ability to memorize training data.
method Randomized algorithm for constructing interpolating neural networks.
result Guarantees that are independent of the number of samples, moving beyond worst-case memorization capacity bounds.
The paper sets limits on neural network sizes based on dataset shapes.
problem Understanding the size of neural networks needed for accurate predictions.
method Examined how the shape of data influences neural network complexity.
result Established upper limits on neural network width based on dataset topology.
Global convergence of multilayer neural networks proven for any depth.
problem Global convergence of multilayer neural networks in the mean field regime.
method Mean field limit framework, neuronal embedding, bidirectional diversity condition.
result Global convergence for multilayer networks of any depths, including correlated initializations.
Simplifies deep learning scaling analysis without sacrificing accuracy.
problem Interpreting feature learning mechanisms and determining network implicit bias in high-dimensional settings.
method Developed a heuristic approach for predicting data and width scales of feature learning patterns.
result Predictions align with known results and extend to complex architectures.
A new neural network model MDRBM improves noise-robustness in classification.
problem Improving noise-robustness in classification problems.
method Stacking a probabilistic-ELM layer on a discriminative restricted Boltzmann machine (DRBM).
result MDRBM outperforms other models, especially in noise-robustness.
PCBM improves neural network generalization by partially observing concepts.
problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.
New AI platform screens portfolios for desirable firms and news.
problem Optimizing portfolio selection with AI.
method Two LLM agents screen for firm fundamentals and news sentiment. Agents deliberate to generate buy/sell signals. High-dimensional estimation determines optimal weights.
result Screened portfolio's Sharpe ratio consistently estimates target, superior to baseline and conventional approaches.
3-layer NTK models generalize better than 2-layer models, especially with large input dimensions.
problem Understanding the generalization of overparameterized neural networks.
method Analyzing the 3-layer NTK model's test error and comparing it to 2-layer NTK models.
result 3-layer NTK models have a faster descent in test error with respect to the number of neurons in the second hidden layer.
In this paper, we prove a conjecture published in 1989 and also partially address an open problem announced at the Conference on Learning Theory (COLT) 2015. With no unrealistic assumption, we first prove the following statements for the squared loss function of deep linear neural networks with any depth and any widths…
A new framework explains GNN predictions by simulating graph structure and feature changes.
problem Lack of transparency in GNN predictions hinders understanding.
method TraP2 framework using a three-layer architecture: Translation, Perturbation, and Paraphrase layers.
result TraP2 achieves 10.2% higher explanation accuracy than state-of-the-art methods.
Examines learning efficiency in neural networks and related models.
problem Analyzing efficiency in deep learning models with singular learning coefficients.
method Examined learning coefficients in neural networks and three-layer neural networks with ReLU units.
result Extended results to include Softmax function, providing a broader understanding of learning efficiency.
This informal technical report details the geometric illustration of decision boundaries for ReLU units in a three layer fully connected neural network. The network is designed and trained to predict pixel intensity from an (x, y) input location. The Geometric Illustration of Neural Networks (GINN) tool was built to vi…
The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.
problem Understanding the compressive limits of Boolean threshold autoencoders.
method Investigation into the minimum number of layers and nodes required for autoencoders to accurately transform binary vectors.
result There exists a seven-layer autoencoder with a logarithmic middle layer size for any set of distinct vectors, but not a three-layer one.
Study improves chiral photonic metasurface design using neural networks and genetic algorithms.
problem Optimizing chiral photonic metasurfaces for high chiral dichroism and reflectivity.
method Combines neural network and genetic algorithm approaches with improved fitness functions and data augmentation.
result Demonstrates a significant increase in chiral dichroism and reflectivity.
FinRL automates trading in quantitative finance with deep reinforcement learning.
problem Steep development curve for traders to automate trading decisions.
method Open-source framework implementing DRL algorithms and reward functions.
result FinRL simplifies strategy design and reduces debugging workloads.
FluxLayer solves cross-chain liquidity fragmentation for better MEV capture.
problem Cross-chain fragmented liquidity and MEV optimization.
method Three-layer framework integrating settlement, intent, and leverage mechanisms.
result FluxLayer enhances cross-chain MEV by capturing more arbitrage opportunities.
SmallML predicts customer churn for SMEs with small data, improving accuracy by 24.2 points.
problem AI exclusion of SMEs due to data scale mismatch.
method Bayesian transfer learning with hierarchical pooling and conformal prediction.
result 96.7% AUC on 100 obs SMEs, 24.2 point improvement over logistic regression.
We analyzed optimism in linear and kernel regression models.
problem Understanding predictive complexity in regression models.
method Derived closed-form asymptotic optimism for linear and kernel regression models.
result Scaled optimism is a useful measure for model complexity.
Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learning models are a major topic of interest. Lipschitz continuous models present a promising approach to solving this problem. By leveraging the …
New approach optimizes sales process for B2B businesses.
problem Optimizing the sales process for B2B businesses.
method Causal Predictive Optimization and Generation with three layers: prediction, optimization, and serving.
result Significant wins over legacy systems in LinkedIn implementation.
In this work, we utilize T1-weighted MR images and StackNet to predict fluid intelligence in adolescents. Our framework includes feature extraction, feature normalization, feature denoising, feature selection, training a StackNet, and predicting fluid intelligence. The extracted feature is the distribution of different…
Robust algorithm for distributed optimization resistant to Byzantine failures.
problem Resilient optimization in the presence of unreliable agents.
method Temporal and spatial robust aggregation, gradient normalization.
result Convergence for strongly convex and non-convex functions.
Framework captures neural network learning in large-width limit.
problem Understanding learning dynamics in large neural networks.
method Developed a rigorous framework for multilayer neural networks in mean field limit.
result Global convergence guarantees for various network architectures and initializations.
A corrective neural network approach improves memorization and learning efficiency.
problem Improving neural network memorization and learning efficiency.
method Divide neural network into groups to sequentially approximate and correct errors.
result Two-layer neural networks can memorize arbitrary labels with optimal number of ReLUs.
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this work, we prove that overparameterized neural networks can learn some notable concept classes, including…
A comparison of SLDS and LSTM for pedestrian behavior prediction shows SLDS works better with shorter sequences.
problem Time-critical pedestrian behavior prediction in autonomous vehicles.
method Comparison of a switching linear dynamical system (SLDS) and a three-layered bi-directional LSTM neural network.
result SLDS achieves higher accuracy with shorter sequences (10 samples) compared to LSTM's 80% accuracy with 100 samples.
Two methods estimate effect size for online experiments, improving accuracy and efficiency.
problem Determining the correct effect size for online experiment duration.
method Two approaches: hierarchical models and utility theory.
result Proposed methods outperform baseline approaches in accuracy and efficiency.
To address potential gaps noted in patient monitoring in the hospital, a novel patient behavior detection system using mmWave radar and deep convolution neural network (CNN), which supports the simultaneous recognition of multiple patients' behaviors in real-time, is proposed. In this study, we use an mmWave radar to t…
Smart mobility management would be an important prerequisite for future fog computing systems. In this research, we propose a learning-based handover optimization for the Internet of Vehicles that would assist the smooth transition of device connections and offloaded tasks between fog nodes. To accomplish this, we make…
Proves deep networks can learn hierarchical structures efficiently.
problem Understanding how deep networks learn hierarchical structures in data.
method Random Hierarchy Models, gradient-based methods, layerwise training.
result Proves deep networks can efficiently learn hierarchical structures.