Derives a family of hyperparameter scaling strategies for neural networks.
problem Optimizing hyperparameters for wide and deep neural networks.
method Introduces a one-parameter family of hyperparameter scaling strategies.
result Reveals proper scaling of depth with width for large-scale models.
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.
Theory predicts neural scaling exponents from language statistics.
problem No existing theory could quantitatively predict neural scaling exponents.
method Isolated two key statistical properties of language.
result Derives a simple formula predicting neural scaling exponents.
Wide neural networks with asymmetrical node scaling converge globally and learn features.
problem Global convergence and feature learning in over-parameterised shallow networks.
method Gradient-based optimisation of wide, shallow neural networks with asymmetrical node scaling.
result Gradient flow and gradient descent converge to a global minimum and learn features, unlike in the NTK parameterisation.
New phases identified in neural scaling laws with compute limits.
problem Understanding neural scaling laws under compute constraints.
method Solved neural scaling model with stochastic gradient descent, derived loss curves, analyzed model-parameter-count phases.
result Identified 4 phases (+3 subphases) in data-complexity/target-complexity phase-plane, derived exponents.
Unintended effects from scaling neural network outputs with adaptive learning rates.
problem Adaptive learning rate optimization's behavior is altered by output scaling, leading to misinterpretation.
method Presented a modified optimization algorithm to mitigate unintended effects.
result Adaptive learning rate's effectiveness is significantly impacted by output scaling, especially for small scaling factors.
Unified scaling laws reveal how model size and training time impact neural network performance.
problem Understanding how much performance improvement can be expected from scaling model size or data volume.
method Established scale-time equivalence and combined it with a linear model analysis of double descent.
result Unified theoretical scaling laws explain previously unexplained phenomena and offer a more accessible path to training large models.
Model shows feature learning can improve neural scaling laws for hard tasks.
problem Understanding and improving neural network scaling laws for various task difficulties.
method Developed a solvable model of neural scaling laws, identified three scaling regimes, and demonstrated feature learning's impact on scaling exponents.
result Feature learning can improve scaling with training time and compute for hard tasks, nearly doubling the exponent.
Study uncovers scaling laws and spectral properties of shallow neural networks.
problem Understanding scaling laws and spectral properties of shallow neural networks.
method Leveraging connections with matrix compressed sensing and LASSO, derived a phase diagram for excess risk.
result Uncovered crossovers between scaling regimes and plateau behaviors, validated empirical observations.
Proposes scale mixture of NNGPs for more flexible stochastic processes.
problem Limited focus on broadening the class of stochastic processes from NNGPs.
method Scale mixture of NNGPs with scale priors on last-layer parameters.
result Turns neural networks into a richer class of stochastic processes.
New neural scaling law found for simple quadratic function.
problem Neural scaling laws and their predictions for model performance.
method Analysis of neural networks, lottery ticket ensembling, statistical interpretation.
result Found a new scaling law (α=1) for a simple quadratic function, contradicting previous theories. Neural networks' performance scales with data size, explained by data manifold dimensionality.
problem Understanding the scaling of neural network performance with the number of parameters.
method Explained by the intrinsic dimension of the data manifold, confirmed through teacher/student framework and various datasets.
result The scaling exponent α is approximately 4 divided by the intrinsic dimension d of the data manifold.
The paper explores neural scaling laws for deep operator networks, offering a theoretical foundation.
problem Understanding neural scaling laws in deep operator networks.
method Theoretical analysis of approximation and generalization errors.
result Established a theoretical framework to quantify neural scaling laws for deep operator networks.
Optimizer choice affects neural scaling laws, changing the exponent α.
problem The exponent α in neural scaling laws L(N)∝N−α varies with the optimizer used. method Controlled random-feature regression experiments with five optimizer variants and six spectral conditions.
result Preconditioned optimizers yield steeper scaling (larger α), with the α-shift increasing across most of the tested spectral range. We propose a system for calculating a "scaling constant" for layers and weights of neural networks. We relate this scaling constant to two important quantities that relate to the optimizability of neural networks, and argue that a network that is "preconditioned" via scaling, in the sense that all weights have the same…
We derive scaling laws for optimizing neural networks in hardware.
problem Optimizing the large parameter space of neural networks in hardware.
method Analytical derivation of scaling laws for Coordinate Descent optimization.
result Convergence is exponential and scales linearly with the number of neurons.
Model predicts neural network performance scaling laws across various factors.
problem Understanding the performance of neural networks across different training factors.
method Random feature model trained with gradient descent, analyzing compute-optimal scaling laws.
result Predicts asymmetric compute-optimal scaling rule and behavior of training and test loss gap.
Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences…
Theory explains neural network scaling with dataset and model size.
problem Neural network scaling laws with dataset and model size.
method Identified variance-limited and resolution-limited scaling behaviors.
result Four scaling regimes explained: infinite data, infinite width, resolution-limited, and large width.
Study reveals neural scaling laws in random graphs and natural language models.
problem Understanding the origin of neural scaling laws in complex systems.
method Examined scaling laws in transformers trained on random walks and simplified natural language models.
result Neural scaling laws emerge in the absence of power law structure in data correlations.
Large models follow power laws in performance with dataset size or parameters.
problem Understanding neural scaling laws in large language models.
method Joint generative data model and random feature model.
result Modeling and solving the dual limit reveals insights into scaling laws.
New method trains shallow neural networks with subquadratic width scaling.
problem Training shallow neural networks with optimal width scaling.
method Polyak-Lojasiewicz condition, smoothness, standard data assumptions, random matrix theory.
result Subquadratic scaling on network width with standard initialization strategies.
New pruning method breaks power law scaling, potentially reducing error to exponential.
problem Improving neural network performance through scaling alone is costly.
method Developed a new data pruning metric to break power law scaling.
result Pruned datasets show better than power law scaling on various image datasets.
Deep ResNets exhibit distinct scaling properties with depth, challenging neural ODE models.
problem Understanding the scaling properties of deep ResNets and their relation to neural ODEs.
method Detailed numerical experiments on weights trained by stochastic gradient descent.
result Deep ResNets can exhibit different scaling regimes, including stochastic differential equations or neither, challenging the neural ODE model.
SHAKE-GNN scales GNNs for large graphs with multi-scale representations.
problem Scaling Graph Neural Networks (GNNs) to large graphs.
method SHAKE-GNN uses a hierarchy of Kirchhoff Forests for stochastic multi-resolution graph decompositions.
result SHAKE-GNN achieves competitive performance on large-scale graph classification benchmarks.
Sharp theory of neural network scaling laws for hierarchical targets.
problem Learning hierarchical multi-index models in neural networks.
method Sharp information-theoretic scaling laws derived for two-layer neural networks.
result Optimal rates achieved by a simple spectral estimator.
This paper explores how neural network width and depth behave as they approach infinity.
problem Understanding the behavior of neural functions as width and depth go to infinity.
method Formal definition of commutativity framework, study of neural covariance kernel, novel proof techniques.
result Taking width and depth to infinity in a deep neural network with skip connections results in the same covariance structure, regardless of the order of taking limits.
New framework for understanding infinite-width neural networks.
problem Understanding the infinite-width limit behavior of neural networks.
method General framework to study limit behavior of neural models based on hyperparameter scaling.
result Derives scaling for existing mean-field and neural tangent kernel limits and introduces new dynamically stable limits.
This work analyzes neural scaling laws using power-law data spectra and derives analytical expressions for generalization error.
problem Understanding how neural network performance scales with key factors like data size and model complexity.
method Statistical mechanics techniques applied to one-pass stochastic gradient descent in a student-teacher framework.
result Derivation of analytical expressions for generalization error under power-law data spectra and identification of conditions for power-law scaling.
Deep neural networks near edge of chaos show universal scaling laws.
problem Understanding the behavior of deep neural networks near critical points.
method Analogy to absorbing phase transitions in statistical mechanics, deterministic propagation dynamics, mean-field and directed percolation universality classes.
result Deep neural networks exhibit universal scaling laws near the edge of chaos.
It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient descent optimize the neural networks in the vector space of weights, which is, however, not positively scale-invariant. This mismatch may lead to…
Recurrent neural networks (RNNs) have been successfully used on a wide range of sequential data problems. A well known difficulty in using RNNs is the \textit{vanishing or exploding gradient} problem. Recently, there have been several different RNN architectures that try to mitigate this issue by maintaining an orthogo…
Study how depth affects inference in deep Bayesian neural networks.
problem Understanding how depth impacts inference in overparameterized linear Bayesian neural networks.
method Interpreting finite deep linear Bayesian neural networks as scale mixtures of Gaussian process predictors.
result Advances analytical understanding of how depth affects inference in a simple class of Bayesian neural networks.
Defines complexity measure for neural networks and feature representations, revealing scaling patterns.
problem Understanding the nonlinearity and dimensionality of neural network computations and feature representations.
method Introduces complexity and effective dimension measures, investigates their dynamics during training, and analyzes their scaling properties.
result Power law scaling of complexity and effective dimension during training, revealing hidden structure of datasets.
A simple model explains inference scaling in neural models.
problem Understanding how model performance improves with repeated inference attempts.
method A statistical ansatz based on memorization to study inference scaling laws.
result Inference loss exhibits a power law decay with increasing trials.
New method μP2 improves neural network training by scaling perturbations layerwise.
problem Improving neural network performance as models scale up.
method Layerwise perturbation scaling in the infinite-width limit of neural networks.
result Layerwise perturbation scaling ensures all layers are effectively perturbed in the limit.
Novel algorithm speeds up log-determinant estimation for large matrices.
problem Efficiently estimating log-determinants of large positive definite matrices under memory constraints.
method Hierarchical algorithm based on block-wise computation of LDL decomposition.
result Accurate estimation of NTK log-determinants from a tiny fraction of the full dataset.
Researchers parallelize neural kernels for large-scale data, achieving state-of-the-art accuracy.
problem Limited scalability of neural kernels on large datasets.
method Massively parallel computation across many GPUs, combined with a distributed, preconditioned conjugate gradients algorithm.
result Achieved state-of-the-art accuracy of 91.2% on CIFAR-5m dataset using neural kernels.
GShard enables scaling of large neural networks with automatic sharding and lightweight APIs.
problem Scaling neural networks to handle vast training data and compute efficiently.
method GShard uses lightweight annotation APIs and XLA compiler extensions for parallel computation.
result GShard successfully trained a 600 billion parameter model on 2048 TPUs in 4 days.
ASAM improves deep neural network generalization by adapting sharpness to scale.
problem Fixed-radius sharpness measure is sensitive to parameter scaling, weakening its connection to generalization.
method Introduces adaptive sharpness, a scale-invariant measure, and proposes ASAM for deep learning.
result ASAM significantly improves model generalization performance across various datasets.
Efficiently applies NTK to large-scale datasets using random features.
problem Computational limitations of kernel methods for large-scale datasets.
method Proposes a sketching-based algorithm combining random features of arc-cosine kernels to construct an efficient feature map of the NTK.
result Achieves comparable error bounds to exact kernel methods but with significantly reduced feature dimensionality.
New neural network method simplifies high-dimensional data.
problem Scalability issues in nonlinear sufficient dimension reduction.
method Stochastic neural network with adaptive gradient algorithm.
result Proposed method outperforms existing methods on large-scale data.
Pruned neural networks' error scales predictably with architecture and task.
problem Understanding the predictability of pruning across different scales and architectures.
method Functionally approximated the error of pruned networks, showing it is predictable in terms of invariant tying width, depth, and pruning level.
result The error of pruned networks follows a scaling law with interpretable coefficients that depend on architecture and task.
BanditLP optimizes personalized recommendations for large-scale systems.
problem Optimizing personalized recommendations for large-scale systems with constraints.
method Unified neural Thompson Sampling for learning and large-scale linear programming for action selection.
result Consistent gains over strong baselines in experiments and business win in LinkedIn's email marketing system.
This study explores training Bayesian neural networks at scale using high-performance computing.
problem Challenges in training Bayesian neural networks at scale due to computational overhead.
method High-performance computing with distributed training, network pruning.
result Pruning up to 80% of the network can reduce inference time by 7.0% without significant accuracy loss.
Three training regimes found for scale-invariant neural networks on the sphere.
problem Training scale-invariant neural networks on the sphere with varying effective learning rate.
method Investigated three regimes of training: convergence, chaotic equilibrium, and divergence.
result Discovered three distinct training regimes with unique characteristics.
Neural HMM with AGA captures multi-scale dynamics in financial markets.
problem Capturing multi-scale temporal dynamics in financial markets.
method Parallel multi-resolution encoders, adaptive gating, and multi-head attention.
result Outperforms fixed-resolution baselines in predicting price movements and liquidity shocks.
Transformer models perform slower than convolutional networks in learning hierarchical language structures.
problem Understanding how neural networks learn hierarchical language structures.
method Theoretical scaling laws and empirical validation of neural network performance.
result Convolutional networks outperform transformers in learning hierarchical language structures.