Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets. More research is focussed on handcrafting complex and larger networks, and the design decisions are often ad-hoc and based on intuition. Some recent research has aimed to demys…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Dynamic Layers”
New GM layers improve neural network performance.
problem Improving neural network performance.
method Employing Gaussian mixture models and Wasserstein gradient flows.
result GM layers achieve comparable performance to two-layer networks.
Paper introduces TSSDMN for modeling dynamic multilayer networks.
problem Capturing temporal and cross-layer dynamics in multilayer networks.
method Tensor State Space Model (TSSDMN) using symmetric Tucker decomposition.
result TSSDMN uniquely captures temporal dynamics within and across layers.
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 regression setting.
Proposes continuous convolution layers for flexible feature map resizing.
problem Fixed stride limitations in discrete convolution layers.
method Introduces Continuous Convolution (CC) layers that use learned continuous functions.
result Dynamic and consistent resizing of feature maps at any scale, non-integer and axis-dependent.
Analyzes SGD dynamics in two-layer networks, bridging different regimes.
problem Understanding SGD dynamics in high-dimensional and mean-field settings.
method Rigorous analysis via deterministic low-dimensional description of sufficient statistics.
result Infinite-width dynamics remains close to a low-dimensional subspace.
Deep equilibrium models converge globally without explicit computation.
problem Global convergence of deep learning models with implicit layers.
method Analysis of gradient dynamics and proof of convergence rate.
result Deep equilibrium models converge to global optimum at a linear rate.
New Banach spaces for ReLU networks enable better function approximation and gradient dynamics analysis.
problem Function approximation and gradient dynamics in multi-layer ReLU networks.
method Developed Banach spaces for ReLU networks, defined new function representations, and analyzed gradient flow dynamics.
result Gradient flow dynamics of the new representation is the continuous analog of gradient descent for ReLU networks.
Study examines infinite limits of transformer dynamics, identifying key parameterizations.
problem Understanding the training dynamics of transformer models in the feature learning regime.
method Analysis of infinite scaling limits using dynamical mean field theory.
result Identified parameterizations that admit well-defined infinite width and depth limits.
Modeling brain dynamics to better understand and control complex behaviors underlying various cognitive brain functions are of interests to engineers, mathematicians, and physicists from the last several decades. With a motivation of developing computationally efficient models of brain dynamics to use in designing cont…
Chaos in cerebellar cells enhances complexity of neural patterns.
problem Understanding how cerebellar granular layer represents complex information.
method Constructed a model of cerebellar granular layer with gap junctions, evaluated using reservoir computing.
result Chaotic dynamics in the cerebellar granular layer produce complex and diverse output patterns.
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.
Study shows how large neural networks avoid overfitting through decoupling of feature learning and complexity growth.
problem Understanding inductive bias and generalization in large neural networks.
method Dynamical mean field theory applied to large two-layer networks.
result Training dynamics of large networks exhibit a separation of timescales, decoupling feature learning and overfitting.
Inverse depth scaling found in LLMs due to similar layers averaging error.
problem Understanding how depth affects loss in large language models.
method Analysis of LLMs and toy residual networks.
result Loss scales inversely proportional to depth in LLMs.
Gradient descent proves global convergence for 4-layer matrix factorization.
problem Global convergence of gradient descent on four-layer matrix factorization under random initialization.
method New techniques to show saddle-avoidance properties and extend eigenvalue theories.
result Polynomial-time global convergence guarantee for randomly initialized gradient descent on four-layer matrix factorization.
The paper studies learning dynamics in two-layer neural networks.
problem Learning dynamics and time scales in two-layer neural networks.
method Gradient flow dynamics of a wide two-layer neural network in high-dimension, with data following a single-index model.
result The learning dynamics exhibit separation of timescales and intermittency.
Predictive Sparse Manifold Transform learns dynamic video sequences.
problem Learning and predicting natural dynamics in video sequences.
method Two-layer framework: sparse coding and manifold learning.
result PSMT with dynamic embedding space outperforms static baselines in future frame prediction.
SSMs combined with neural networks match Transformers in dynamic token selection.
problem Understanding the capabilities of SSMs in dynamic token selection.
method Exploring SSMs combined with fully connected neural networks.
result SSMs combined with nonlinear layers can efficiently solve challenging tasks and estimate functions.
While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we argue their binary deci…
This study analyzes how one-layer transformers learn regular language recognition tasks.
problem Understanding how one-layer transformers solve regular language recognition tasks like even pairs and parity check.
method Theoretical analysis of training dynamics and gradient descent for a one-layer transformer.
result A one-layer transformer can solve even pairs directly but needs CoT for parity check. Training phases show rapid growth in attention layer followed by logarithmic growth in linear layer.
Two-layer neural networks learn efficiently using kernel methods in mean-field analysis.
problem Feature learning ability of two-layer neural networks in the mean-field regime.
method Mean-field analysis through kernel methods, focusing on dynamics of the first layer's kernel.
result Two-layer neural networks can learn a union of multiple reproducing kernel Hilbert spaces more efficiently than kernel methods.
Enhanced deep learning model forecasts household leverage series accurately.
problem Forecasting household leverage series due to complex temporal-spatial dynamics.
method TSEN model with multiple RNN-based layers and an attention layer.
result Captures temporal-spatial dynamics and provides more accurate predictions.
Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of layers, especially considering different computational needs of a sequence. We propose a layer flexible recurrent neural network with adapt…
MI-GAN solves OPF with renewable uncertainty using model-informed layers.
problem Optimal Power Flow (OPF) under renewable uncertainty.
method Model-Informed Generative Adversarial Network (MI-GAN) framework with three layers.
result MI-GAN improves solution feasibility and optimality.
New cooperative dynamics enhances retrieval performance in neural networks.
problem Understanding emergent computational capabilities in disordered systems.
method Leveraging statistical mechanics, extended neural network architecture for hetero-associative memory.
result Layers trained with less informative datasets develop retrieval regions of the same amplitude, leading to optimal performance.
Study on symmetries in wide neural networks' dynamics without bias.
problem Understanding symmetries in the dynamics of wide two-layer neural networks.
method Analyzing symmetries in gradient flow on population risk for infinitely wide networks.
result Symmetries can simplify the dynamics of predictors and reduce the dimensionality of the problem.
Transformers can learn noisy linear systems with depth and IID data.
problem Learning noisy linear dynamical systems with transformers.
method Theoretical analysis of multi-layer and single-layer transformers with respect to -testing loss.
result Single-layer transformers have a non-diminishing lower bound on approximation error, suggesting depth separation.
Paper analyzes Transformer learning dynamics, proving benign landscape for in-context learning.
problem Understanding how Transformers learn in context with nonlinear features.
method Mean-field and two-timescale analysis of Transformer dynamics, proving nonconvex but benign landscape.
result Proves mean-field dynamics avoid saddle points, leading to improved optimization.
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant also in the calculation of the dot product ("convolution") in a 1-D convolution layer. In this work a method is proposed for aligning the conv…
A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are updated. General initialization schemes as well as general regimes for the network width and training data size are considered. In the over-…
This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes is used to dynamically set the learning rate of the network through the trainin…
Two-layer networks learn faster with batch reuse, overcoming information and leap exponents.
problem Limitations of gradient flow and single-pass GD in learning multi-index target functions.
method Multi-pass gradient descent that reuses batches, analyzed using Dynamical Mean-Field Theory.
result Two-time-step overlap with target subspace for non-staircase functions, overcoming information and leap exponents.
This work defines a new function space for multi-layer neural networks.
problem Characterizing the function space of multi-layer neural networks.
method Defining a neural Hilbert ladder (NHL) as an infinite union of reproducing kernel Hilbert spaces (RKHSs).
result Established theoretical properties of the new function space, including generalization guarantees and dynamics of random fields.
On the reduction of nonlinear electromechanical systemsphysics.class-ph
Reduces nonlinear electromechanical dynamics through quasi-steady state hypothesis.
problem Nonlinear dynamics of electromechanical systems.
method Quasi-steady state hypothesis, non-dimensionalization, scaling.
result Physical justification and characteristic time scales of dynamics.
Gradient descent trains both layers of a ReLU network to fit a linear model.
problem Training dynamics of a ReLU network to fit a linear target function.
method Jointly training both layers of a one-hidden-layer ReLU network in a realizable setting with Gaussian inputs and labels.
result Gradient descent from a small random initialization converges to a global minimizer at a linear rate with optimal sample complexity.
Study reveals conditions for neural networks to forget learned features.
problem Understanding feature unlearning in neural networks.
method Infinite-width limit analysis with stochastic gradient descent, fast-slow dynamics.
result Conditions for feature unlearning are determined by the strength of nonlinear terms and initial weights.
This work relaxes energy constraints in self-attention layers for a more general analysis.
problem Understanding inherent biases and dynamics in self-attention layers without energy functions.
method Dynamical systems analysis and Jacobian matrix examination.
result Normalized dynamics are close to a critical state, indicating high inference performance.
Reservoir Computing (RC) is a popular methodology for the efficient design of Recurrent Neural Networks (RNNs). Recently, the advantages of the RC approach have been extended to the context of multi-layered RNNs, with the introduction of the Deep Echo State Network (DeepESN) model. In this paper, we study the quality o…
Gradient descent dynamics in neural networks show quenching and activation phases.
problem Understanding training dynamics in neural networks.
method Numerical and phenomenological study of gradient descent algorithm for two-layer neural networks.
result Gradient descent dynamics exhibit quenching and activation phases in under-parametrized networks.
This paper introduces a hierarchical associative memory model with multiple layers.
problem Limitations of traditional associative memory models with only one hidden layer.
method Develops a fully recurrent model with arbitrary layers, including locally connected ones, and a corresponding energy function.
result The model can dynamically assemble memories using weights from lower layers and higher layers' rules.
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setupstat.ML
Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural networks in the teacher-student setup, where one network, the student, is trained…
ADMP-GNN dynamically adjusts message-passing layers for better graph learning performance.
problem Fixed message-passing steps in GNNs do not account for nodes' varying computational needs.
method Proposes ADMP-GNN, which dynamically adjusts the number of message-passing layers for each node.
result Improves performance on node classification tasks compared to baseline GNN models.
MTAdam optimizes multiple loss terms in neural models, balancing gradients dynamically.
problem Balancing multiple loss terms in neural model training is challenging and computationally demanding.
method Generalized Adam algorithm that computes separate derivatives and balances gradients across layers dynamically.
result Training with MTAdam leads to faster recovery from suboptimal initial loss weighting and matches conventional training outcomes.
A simple gating mechanism improves deep learning convergence.
problem Vanishing or exploding gradients in deep networks.
method Introducing a zero-initialized parameter to each residual connection.
result Training deep networks (up to 120 layers) with fast convergence and better performance.
Efficiently predicts long-time dynamics of quantum spin models using MLP regression.
problem Challenges in calculating long-time expectation values for quantum spin models.
method Utilized a multi-layer perceptron (MLP) model for regression on matrix product states (MPS) expectation values.
result Significantly reduced computational cost for generating long-time dynamics while maintaining high accuracy.
Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layerscs.LG
Dynamic Sparse Training finds efficient sparse networks from scratch.
problem Finding efficient sparse neural networks.
method Jointly optimizes network parameters and sparsity with trainable thresholds.
result Achieves state-of-the-art performance with minimal performance loss.
The paper analyzes SGD in high-dimensional networks, revealing new scaling limits.
problem Understanding SGD dynamics in high-dimensional networks.
method Analyzing the effective dynamics of SGD using recent work on the subject.
result A new correction term emerges at the critical scaling regime, changing the phase diagram.
This paper presents a phase diagram for two-layer neural networks under different initialization scales.
problem Understanding the behavior of neural networks under varying scales of initialization.
method Analysis of a phase diagram for two-layer neural networks.
result Condensation of weight vectors on isolated orientations during training.