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.
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…
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.
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.
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.
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.
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.
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.
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…
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.
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.
A fundamental question in deep learning concerns the role played by individual layers in a deep neural network (DNN) and the transferable properties of the data representations which they learn. To the extent that layers have clear roles, one should be able to optimize them separately using layer-wise loss functions. S…
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.
Efficiently trains GCNs with reduced time and memory usage.
problem Hard training of GCNs over large graph datasets.
method Layer-wise and learned efficient training framework (L2-GCN). result Significantly reduces training time and memory usage.
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…
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.
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.
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.
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with mom…
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.
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.
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.
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.
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.
Designs a neural network to reduce training cost by mapping to higher dimensions.
problem High training cost in neural networks.
method Maps feature vectors to higher dimensional space, designs weight matrices to reduce cost, uses convex constraints.
result Reduces training cost as the number of layers increases, without cross-validation.
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.
TempBalance boosts model performance with low data.
problem Low-data training and fine-tuning in model alignment.
method Inspired by HT-SR theory, TempBalance balances training quality across layers.
result TempBalance improves model performance as data decreases.
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 …
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.
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 …
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…
Backpropagation-free RL method trains layers using local signals.
problem Vanishing or exploding gradients in backpropagation-based RL.
method Local pairwise distance matching for layer-wise training without backpropagation.
result Backpropagation-free method achieves competitive performance and stability.
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.
Study on rich regime training in deep learning, finding active parameters in bottom layers.
problem Understanding the practical success of deep learning models.
method Empirical study on rich regime training with benchmark datasets, re-initialization analysis, and probabilistic Layer-Wise Sparse SGD.
result Probabilistic Layer-Wise Sparse SGD matches vanilla SGD's generalization performance with improved efficiency.
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…
New analysis enables inversion of deep generative models with unique solutions.
problem Inverting deep generative models like GANs and VAEs.
method Sparse representation theory and layer-wise inversion pursuit algorithms.
result Invertible solutions for generative models with unique latent vectors.
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…
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.
XAI identifies key time steps for early crop classification.
problem Early crop classification with high accuracy and timeliness.
method Training a baseline model with LRP to identify important time steps.
result Identified a 21st April 2019 to 9th August 2019 timeframe with 0.75% accuracy loss.
DR technique helps deep models learn faster and better.
problem Vanishing gradients and local minima in deep model training.
method DR technique applies penalties on hidden units to improve learning.
result DR improves convergence and generalization in deep neural networks.
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…
MPE framework proves universal approximation for quantum data distribution.
problem Challenges in generating quantum data from underlying distributions.
method Many-body Projected Ensemble (MPE) framework for quantum state design.
result MPE can approximate any quantum distribution within 1-Wasserstein distance error.
New method improves accuracy of quantized neural networks.
problem Accuracy drop in quantized neural networks, especially MobileNet family.
method Weight equalizing shift scaler, binary shifting to recover output range.
result Top-1 accuracy improved from 0.1% to 69.78% ~ 70.96% in MobileNets.
Various forms of representations may arise in the many layers embedded in deep neural networks (DNNs). Of these, where can we find the most compact representation? We propose to use a pruning framework to answer this question: How compact can each layer be compressed, without losing performance? Most of the existing DN…
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training. The approach employs additional modules called local critic networks besides the main network model to be trained, which are used to obtain error gradients without complete feedforward …
New method for efficient proximal mapping of 1-path-norm in shallow networks.
problem Efficiently handling the 1-path-norm of shallow neural networks.
method Closed-form proximal operator for efficient computation and upper bound on Lipschitz constant.
result Proximal mapping allows robust training against adversarial perturbations.