Layer-wise preconditioning methods improve neural network optimization and feature learning.
problem Suboptimal feature learning in standard optimization algorithms.
method Layer-wise preconditioning methods that introduce preconditioners per axis of each layer's weight tensors.
result Layer-wise preconditioning is necessary for provable feature learning in linear and single-index models.
Unified framework LPCD optimizes quantization of complex submodules.
problem Quantization of complex submodules in neural networks.
method Layer-Projected Coordinate Descent (LPCD) for quantizing arbitrary submodules.
result LPCD enhances both layer-wise PTQ methods and existing submodule approaches.
New loss functions reveal layer roles in deep neural networks.
problem Understanding the role of individual layers in deep neural networks.
method Derived Deep Gaussian Layer-wise loss functions (DGLs) using Gaussian Processes and SGD.
result First explicit and competitive layer-wise loss functions for deep neural networks.
Layer-wise training for deep linear networks achieves faster convergence with optimal learning rate.
problem Training deep neural networks is challenging; layer-wise training is proposed as an alternative.
method Layer-wise training using block coordinate gradient descent (BCGD) with orthogonal-like initialization.
result The optimal learning rate guarantees the fastest decrease in loss and is applicable without prior knowledge.
We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machin…
Proposes QEP to mitigate quantization error propagation in layer-wise post-training quantization.
problem Growth of quantization errors across layers degrades performance, especially in low-bit regimes.
method Quantization Error Propagation (QEP) framework that explicitly propagates and compensates for quantization errors.
result QEP-enhanced layer-wise PTQ achieves substantially higher accuracy, especially in low-bit regimes.
Gluon optimizes LMO-based methods for large-scale tasks, improving performance and theory-practice gap.
problem LMO-based methods lack theoretical support for practical implementation and smoothness assumptions.
method Introduces Gluon, a new LMO-based method with refined smoothness model.
result Gluon's theoretical stepsizes match fine-tuned values, closing the theory-practice gap.
LAGS-SGD optimizes deep learning training by sparsifying gradients layer-wise.
problem Reduces long training times in large deep neural networks with distributed S-SGD.
method Layer-wise adaptive gradient sparsification combined with S-SGD.
result LAGS-SGD achieves convergence guarantees and outperforms vanilla S-SGD.
Physics-inspired methods optimize SVD compression of LLMs.
problem Efficiently compressing large language models (LLMs) using SVD.
method FermiGrad for globally optimal rank selection and PivGa for lossless compression.
result Global optimization of SVD ranks and lossless compression of low-rank factors.
Layer-wise networks have a closed-form solution and a stopping criterion.
problem Training networks one layer at a time without backpropagation.
method Proved the Kernel Mean Embedding as the closed-form solution and developed a stopping criterion.
result Layer-wise networks converge to a highly desirable kernel for classification.
Drop-Muon updates only some layers, speeding up training.
problem Conventional deep learning optimizers update all layers at once, which can be inefficient.
method Drop-Muon updates only a subset of layers per step, with randomized schedules.
result Drop-Muon achieves up to 1.4x faster training time with similar accuracy.
Layer-wise networks have a closed-form solution and a stopping criterion.
problem Training networks one layer at a time without backpropagation.
method Proved the closed-form solution using the kernel Mean Embedding and Neural Indicator Kernel.
result Layer-wise networks have a closed-form solution and a stopping criterion.
NovoGrad improves deep learning training with adaptive moments and layer-wise normalization.
problem Training deep neural networks efficiently and effectively.
method Layer-wise adaptive moments with gradient normalization and decoupled weight decay.
result NovoGrad outperforms well-tuned SGD with momentum and Adam/AdamW in various tasks.
A new decentralized deep learning method reduces communication costs without sacrificing accuracy.
problem Efficient decentralized deep learning with reduced communication costs.
method Layer-wise federated group ADMM (L-FGADMM) with adjusted communication periods for different layers.
result By skipping the largest layer consensus, L-FGADMM achieves similar test accuracy to federated learning with significantly reduced communication cost.
Large batch training improves deep learning performance without needing warmup.
problem Slow convergence at early epochs in large batch training.
method Proposes CLARS algorithm and analyzes convergence rate.
result Proposed algorithm outperforms gradual warmup and state-of-the-art large-batch optimizers.
In this paper, we tackle the problem of explanations in a deep-learning based model for recommendations by leveraging the technique of layer-wise relevance propagation. We use a Deep Convolutional Neural Network to extract relevant features from the input images before identifying similarity between the images in featu…
LEWIS merges LLMs without training, improving performance on specific tasks.
problem Limited performance improvement of merged models on specific benchmarks.
method Guided model merging using layer-wise sparsity and task-vector pruning.
result Improved model performance by up to 11.3% on math-solving tasks.
Random layer-wise pruning profiles are as effective as metric-based ones for various datasets.
problem Reduction of model size and computational resources in neural networks.
method Conducted baseline experiments, developed RL-based search algorithm for finding transferable layer-wise pruning profiles.
result RL-based layer-wise pruning profiles are as good or better than best profiles found on the original dataset via exhaustive search.
Low complexity decentralized neural net with centralized performance.
problem Training large neural networks in distributed nodes without data sharing.
method Layer-wise learning using ADMM for low complexity and centralized performance.
result Equivalent learning performance to centralized training in distributed nodes.
Analyzes layer-wise quantization effects in neural networks.
problem Identifying and fixing degradation in quantized neural networks.
method Layer-wise quantization analysis framework.
result Local fixes can significantly reduce quantization degradation.
Automatically learns flexible symmetry constraints in neural networks using gradients.
problem Fixed hard constraints on neural network functions that cannot be adapted.
method Improves parameterisations of soft equivariance and optimizes marginal likelihood using differentiable Laplace approximations.
result Achieves equivalent or improved performance on image classification tasks compared to baselines with hard-coded symmetry.
Improves synthetic-to-real generalization without real data.
problem Synthetic models struggle with real data generalization.
method Encourages similar ImageNet representations and automates learning rates.
result Significant improvement in synthetic-to-real generalization.
A new method improves few-shot image classification by updating top layers.
problem Few-shot image classification with limited data.
method Layer-wise adaptive updating (LWAU) for meta-learning.
result LWAU outperforms existing methods with a clear margin and learns more efficiently.
Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise pre-training has found strong theoretical foundation and broad empirical support. Howe…
DSA efficiently allocates sparsity across layers for budgeted pruning.
problem Efficiently distributing resources (sparsity) across layers in pruning under resource constraints.
method DSA uses differentiable pruning to find continuous layer-wise pruning ratios via gradient-based optimization.
result DSA achieves superior performance and significantly reduces the time cost of pruning.
Joslim optimizes both width and weight configurations for slimmable neural networks, improving model efficiency.
problem Optimizing both width and weight configurations for slimmable neural networks to improve efficiency.
method Proposes a general framework for joint optimization of width configurations and weights, and introduces Joslim algorithm.
result Improves model efficiency by up to 1.7% in top-1 accuracy on the ImageNet dataset.
Speeds up deep neural networks training by 10x using GPU concurrency.
problem Training deep residual neural networks efficiently.
method Layer-wise parallel training with GPU concurrency and Nonlinear Multigrid.
result 10.2x speedup over traditional techniques.
Study on shortcuts in deep networks, revealing their layer-wise distribution and impact.
problem Understudied impact of shortcuts on feature representations in deep networks.
method Layer-wise localization through counterfactual training on clean and skewed datasets.
result Shortcuts are distributed throughout the network, not localized in specific layers.
EF21-Muon optimizes deep learning with error feedback, improving efficiency and accuracy.
problem Lack of principled distributed frameworks for non-Euclidean LMO-based optimizers.
method Introduces EF21-Muon, a communication-efficient, non-Euclidean LMO-based optimizer with convergence guarantees.
result First efficient distributed implementation of non-Euclidean LMO-based optimizers, achieving up to 7x communication savings.
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Despite their great success in practical applications, there is still a lack of theoretical and systematic methods to analyze deep neural networks. In this paper, we illustrate an advanced information theoretic methodology to understand the dynamics of learning and the design of autoencoders, a special type of deep lea…
We establish the first benchmark for federated learning with differential privacy in ASR, achieving competitive performance.
problem Challenges in training large transformer models for ASR in federated learning with differential privacy.
method Per-layer clipping and layer-wise gradient normalization to mitigate gradient heterogeneity.
result FL with DP is viable in ASR with strong privacy guarantees, achieving competitive performance.
This work analyzes how different layers in deep neural networks contribute to generalization error.
problem Understanding the role of each layer in deep neural networks for generalization.
method Spectral analysis, Neural Tangent Kernel, Hermite polynomials, Spherical Harmonics.
result Initial layers in deep neural networks have a larger bias towards high-frequency functions.
Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an update direction for the weights. An alternative approach is to train the network …
We propose a novel family of connectionist models based on kernel machines and consider the problem of learning layer-by-layer a compositional hypothesis class, i.e., a feedforward, multilayer architecture, in a supervised setting. In terms of the models, we present a principled method to "kernelize" (partly or complet…
QuantEase optimizes LLMs with CD-based quantization, achieving state-of-the-art performance.
problem Efficiently quantize large language models for deployment.
method Layer-wise quantization using CD-based algorithms with matrix and vector operations.
result State-of-the-art performance in perplexity and zero-shot accuracy.
This work improves OOD detection using deep generative models by approximating Fisher information metrics.
problem Deep generative models often incorrectly infer higher likelihoods for out-of-distribution data.
method Approximating Fisher information metrics using gradient norms of data points.
result The method outperforms existing OOD detection techniques.
Adapts LRP for LSTM to explain sequential data.
problem Lack of explainable AI for LSTM models.
method Extends LRP to LSTM, introduces new propagation scheme.
result Delivers faithful explanations for LSTM predictions.
RedEx improves neural network optimization with convex optimization guarantees.
problem Difficult optimization of neural networks.
method RedEx architecture using convex optimization with semi-definite constraints.
result RedEx can efficiently learn functions fixed methods cannot.
Improved neural quantization reduces accuracy loss to less than 1% with 4-bit weights.
problem Reducing accuracy loss in neural quantization below 8-bits.
method Layer-wise calibration and integer programming to optimize bit-width allocation.
result Less than 1% accuracy degradation with 4-bit weights and activations.
InteractionNet models noncovalent protein-ligand interactions with GNNs and explains predictions.
problem Modeling noncovalent protein-ligand interactions with graph neural networks.
method InteractionNet uses a GNN architecture with separated covalent and noncovalent convolution layers and layer-wise relevance propagation for explainability.
result InteractionNet successfully predicts noncovalent protein-ligand interactions with chemical relevance.
Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we formulate the multi-layered network as a Markov chain, introducing a training met…
Few-shot network compression improves accuracy with minimal data.
problem High estimation errors from original network during inference.
method Cross distillation, layer-wise knowledge distillation approach.
result Cross distillation significantly improves student network's accuracy with few training instances.
TempBalance improves neural network training by balancing learning rates across layers.
problem Improving neural network training performance.
method Layer-wise learning rate scheduling based on HT-SR Theory.
result TempBalance significantly outperforms ordinary SGD and state-of-the-art optimizers.
Locally adaptive activation functions boost deep and physics-informed neural networks.
problem Improving the performance and training speed of deep and physics-informed neural networks.
method Layer-wise and neuron-wise locally adaptive activation functions with a slope recovery term.
result The proposed methods accelerate convergence and reduce training cost.
When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is based on an optimistic proxy of future performance, the best latent marginal. W…
Standard optimizers perform as well as LARS and LAMB at large batch sizes.
problem Comparing optimizers for neural network training at large batch sizes.
method Used standard optimizers like Nesterov momentum and Adam to match or exceed LARS and LAMB results.
result Standard optimizers can match or exceed LARS and LAMB at large batch sizes.
A new method prevents forgetting during knowledge transfer.
problem Catastrophic forgetting in transfer learning.
method Transfer without Forgetting (TwF) using a fixed pretrained network.
result TwF outperforms other CL methods by 4.81% in Class-Incremental accuracy.