Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only high-quality data based on a score function (human or machine feedback). Previous work Feng et al. (2024) analyzed models trained on synthetic data as sample size increases. We extend this by using random matrix theory to derive the performance of a binary classifier trained on a mix of real and pruned synthetic data in a high dimensional setting. Our findings identify conditions where synthetic data could improve performance, focusing on the quality of the generative model and verification strategy. We also show a smooth phase transition in synthetic label noise, contrasting with prior sharp behavior in infinite sample limits. Experiments with toy models and large language models validate our theoretical results.

We introduce an analytical framework to quantify the changes in a machine learning algorithm's output distribution following the inclusion of a few data points in its training set, a notion we define as leave-one-out distinguishability (LOOD). This is key to measuring data **memorization** and information **leakage** as well as the **influence** of training data points in machine learning. We illustrate how our method broadens and refines existing empirical measures of memorization and privacy risks associated with training data. We use Gaussian processes to model the randomness of machine learning algorithms, and validate LOOD with extensive empirical analysis of leakage using membership inference attacks. Our analytical framework enables us to investigate the causes of leakage and where the leakage is high. For example, we analyze the influence of activation functions, on data memorization. Additionally, our method allows us to identify queries that disclose the most information about the training data in the leave-one-out setting. We illustrate how optimal queries can be used for accurate **reconstruction** of training data.

Empirical studies have consistently demonstrated that increasing the size of neural networks often yields superior performance in practical applications. However, there is a lack of consensus regarding the appropriate scaling strategy, particularly when it comes to increasing the depth of neural networks. In practice, excessively large depths can lead to model performance degradation. In this paper, we introduce Depth-$\mu$P, a principled approach for depth scaling, allowing for the training of arbitrarily deep architectures while maximizing feature learning and diversity among nearby layers. Our method involves dividing the contribution of each residual block and the parameter update by the square root of the depth. Through the use of Tensor Programs, we rigorously establish the existence of a limit for infinitely deep neural networks under the proposed scaling scheme. This scaling strategy ensures more stable training for deep neural networks and guarantees the transferability of hyperparameters from shallow to deep models. To substantiate the efficacy of our scaling method, we conduct empirical validation on neural networks with depths up to $2^{10}$.

In this paper, we show that Low Rank Adaptation (LoRA) as originally introduced in (Hu et al., 2021) leads to suboptimal finetuning of models with large width. This is due to the fact that adapter matrices A and B in LoRA are updated with the same learning rate in ADAM. Using scaling arguments for large width networks, we demonstrate that the same learning rate does not allow efficient feature learning. We then show that this suboptimality of LoRA can be corrected simply by setting different learning rates for the LoRA adapter matrices A and B with a well-chosen fixed ratio. We call this proposed algorithm LoRA+. In our extensive experiments, LoRA+ improves finetuning speed (up to ∼ 2X SpeedUp) and performance (1% − 2% improvements), at the same computational cost as LoRA. The code is available at https://github.com/nikhil-ghosh-berkeley/loraplus

In this paper, we study the role of initialization in Low Rank Adaptation (LoRA) as originally introduced in Hu et al. (2021). Essentially, to start from the pretrained model, one can either initialize $B$ to zero and $A$ to random, or vice-versa. In both cases, the product $BA$ is equal to zero at initialization, which makes finetuning starts from the pretrained model. These two initialization schemes are seemingly similar. They should in-principle yield the same performance and share the same optimal learning rate. We demonstrate that this is an *incorrect intuition* and that the first scheme (of initializing $B$ to zero and $A$ to random) on average in our experiments yields better performance compared to the other scheme. Our theoretical analysis shows that the reason behind this might be that the first initialization allows the use of larger learning rates (without causing output instability) compared to the second initialization, resulting in more efficient learning of the first scheme. We validate our results with extensive experiments on LLMs.

In this paper, we study the commutativity of infinite width and depth limits in deep neural networks. Our aim is to understand the behavior of neural functions (functions that depend on a neural network model) as width and depth go to infinity (in some sense), and eventually identify settings under which commutativity holds, i.e. the neural function tends to the same limit no matter how width and depth limits are taken. In this paper, we formally introduce and define the commutativity framework, and discuss its implications on neural network design and scaling. We study commutativity for the neural covariance kernel which reflects how network layers separate data. Our findings extend previous results established in Hayou and Yang (2023) by showing that taking the width and depth to infinity in a deep neural network with skip connections, when branches are suitably scaled to avoid exploding behavior, result in the same covariance structure no matter how that limit is taken. This has a number of theoretical and practical implications that we discuss in the paper. The proof techniques in this paper are new and rely on tools that are more accessible to readers who are not familiar with stochastic calculus (used in the proofs of Hayou and Yang (2023)).

We show that taking the width and depth to infinity in a deep neural network with skip connections, when branches are scaled by $1/\sqrt{depth}$, result in the same covariance structure no matter how that limit is taken. This explains why the standard infinite-width-then-depth approach provides practical insights even for networks with depth of the same order as width. We also demonstrate that the pre-activations, in this case, have Gaussian distributions which has direct applications in Bayesian deep learning. We conduct extensive simulations that show an excellent match with our theoretical findings.

Recent work by Baratin et al. (2021) sheds light on an intriguing pattern that occurs during the training of deep neural networks: some layers align much more with data compared to other layers (where the alignment is defined as the normalize euclidean product of the tangent features matrix and the data labels matrix). The curve of the alignment as a function of layer index (generally) exhibits a ascent-descent pattern where the maximum is reached for some hidden layer. In this work, we provide the first explanation for this phenomenon. We introduce the Equilibrium Hypothesis which connects this alignment pattern to signal propagation in deep neural networks. Our experiments demonstrate an excellent match with the theoretical predictions.

Deep ResNet architectures have achieved state of the art performance on many tasks. While they solve the problem of gradient vanishing, they might suffer from gradient exploding as the depth becomes large (Yang et al. 2017). Moreover, recent results have shown that ResNet might lose expressivity as the depth goes to infinity (Yang et al. 2017, Hayou et al. 2019). To resolve these issues, we introduce a new class of ResNet architectures, calledStable ResNet, that have the property of stabilizing the gradient while ensuring expressivity in the infinite depth limit.

Regularization plays a major role in modern deep learning. From classic techniques such as L1, L2 penalties to other noise-based methods such as Dropout, regularization often yields better generalization properties by avoiding overfitting. Recently, Stochastic Depth (SD) has emerged as an alternative regularization technique for residual neural networks (ResNets) and has proven to boost the performance of ResNet on many tasks [Huang et al., 2016]. Despite the recent success of SD, little is known about this technique from a theoretical perspective. This paper provides a hybrid analysis combining perturbation analysis and signal propagation to shed light on different regularization effects of SD. Our analysis allows us to derive principled guidelines for choosing the survival rates used for training with SD.

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward propagation and the exponential vanishing/exploding of gradients during back-propagation. Understanding the theoretical properties of untrained random networks is key to identifying which deep networks may be trained successfully as recently demonstrated by Samuel et al. (2017) who showed that for deep feedforward neural networks only a specific choice of hyperparameters known as the ‘Edge of Chaos’ can lead to good performance. While the work by Samuel et al. (2017) discuss trainability issues, we focus here on training acceleration and overall performance. We give a comprehensive theoretical analysis of the Edge of Chaos and show that we can indeed tune the initialization parameters and the activation function in order to accelerate the training and improve the performance.