学习排序

We propose SLoPe, a Double-Pruned **S**parse Plus **L**azy L**o**w-rank Adapter **P**r**e**training method for LLMs that improves the accuracy of sparse LLMs while accelerating their pretraining and inference and reducing their memory footprint. Sparse pretraining of LLMs reduces the accuracy of the model, to overcome this, prior work uses dense models during fine-tuning. SLoPe improves the accuracy of sparsely pretrained models by adding low-rank adapters in the final 1% iterations of pretraining without adding significant overheads to the model pretraining and inference. In addition, SLoPe uses a double-pruned backward pass formulation that prunes the transposed weight matrix using N:M sparsity structures to enable an accelerated sparse backward pass. SLoPe accelerates the training and inference of models with billions of parameters up to 1.25× and 1.54× respectively (OPT-33B and OPT-66B) while reducing their memory usage by up to 0.63× and 0.61× for training and inference respectively.

The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These challenges can undermine model generalization across tasks, resulting in reduced downstream performance. Recent research suggests that fine-tuning LLMs on carefully selected, task-specific subsets of data can match or even surpass the performance of using the entire dataset. Building on these insights, we propose the Ensembles of Low-Rank Expert Adapters (ELREA) framework to improve the model's capability to handle diverse tasks. ELREA clusters the training instructions based on their gradient directions, representing different areas of expertise and thereby reducing conflicts during optimization. Expert adapters are then trained on these clusters, utilizing the low-rank adaptation (LoRA) technique to ensure training efficiency and model scalability. During inference, ELREA combines predictions from the most relevant expert adapters based on the input data's gradient similarity to the training clusters, ensuring optimal adapter selection for each task. Experiments show that our method outperforms baseline LoRA adapters trained on the full dataset and other ensemble approaches with similar training and inference complexity across a range of domain-specific tasks.

Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models. Despite its computational efficiency, LoRA still yields inferior performance compared to full fine-tuning. In this paper, we first uncover a fundamental connection between the optimization processes of LoRA and full fine-tuning: using LoRA for optimization is mathematically equivalent to full fine-tuning using a low-rank gradient for parameter updates. And this low-rank gradient can be expressed in terms of the gradients of the two low-rank matrices in LoRA. Leveraging this insight, we introduce LoRA-Pro, a method that enhances LoRA's performance by strategically adjusting the gradients of these low-rank matrices. This adjustment allows the low-rank gradient to more accurately approximate the full fine-tuning gradient, thereby narrowing the performance gap between LoRA and full fine-tuning. Furthermore, we theoretically derive the optimal solutions for adjusting the gradients of the low-rank matrices, applying them during fine-tuning in LoRA-Pro. We conduct extensive experiments across natural language understanding, dialogue generation, mathematical reasoning, code generation, and image classification tasks, demonstrating that LoRA-Pro substantially improves LoRA's performance, effectively narrowing the gap with full fine-tuning. Our code is publicly available at https://github.com/mrflogs/LoRA-Pro.

Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learning. These techniques significantly lower the number of parameters, striking a balance between compactness and performance. However, a common challenge has been the compromise between parameter efficiency and the accuracy of the model, where reduced parameters often lead to diminished accuracy compared to their full-rank counterparts. In this work, we propose a novel theoretical framework that integrates a sinusoidal function within the low-rank decomposition process. This approach not only preserves the benefits of the parameter efficiency characteristic of low-rank methods but also increases the decomposition's rank, thereby enhancing model performance. Our method proves to be a plug in enhancement for existing low-rank models, as evidenced by its successful application in Vision Transformers (ViT), Large Language Models (LLMs), Neural Radiance Fields (NeRF) and 3D shape modelling.

Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tenors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference-time LLM memory usage. Palu decomposes the linear layers into low-rank matrices, caches compressed intermediate states, and reconstructs the full keys and values on the fly. To improve accuracy, compression rate, and efficiency, Palu further encompasses (1) a medium-grained low-rank decomposition scheme, (2) an efficient rank search algorithm, (3) low-rank-aware quantization compatibility enhancements, and (4) an optimized GPU kernel with matrix fusion. Extensive experiments with popular LLMs show that Palu compresses KV-Cache by 50% while maintaining strong accuracy and delivering up to 1.89× speedup on the RoPE-based attention module. When combined with quantization, Palu’s inherent quantization-friendly design yields small to negligible extra accuracy degradation while saving additional memory than quantization-only methods and achieving up to 2.91× speedup for the RoPE-based attention. Moreover, it maintains comparable or even better accuracy (up to 1.19 lower perplexity) compared to quantization-only methods. These results demonstrate Palu’s superior capability to effectively address the efficiency and memory challenges of LLM inference posed by KV-Cache. Our code is publicly available at: https://github.com/shadowpa0327/Palu.

Recent works show we can linearize large language models (LLMs)—swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention—avoiding the expensive pretraining costs. However, linearizing LLMs often significantly degrades model quality, still requires training over billions of tokens, and remains limited to smaller 1.3B to 7B LLMs. We thus propose Low-rank Linear Conversion via Attention Transfer (LoLCATs), a simple two-step method that improves LLM linearizing quality with orders of magnitudes less memory and compute. We base these steps on two findings. First, we can replace an LLM's softmax attentions with closely-approximating linear attentions, simply by *training* the linear attentions to match their softmax counterparts with an output MSE loss (“attention transfer”). Then, this enables adjusting for approximation errors and recovering LLM quality simply with *low-rank* adaptation (LoRA). LoLCATs significantly improves linearizing quality, training efficiency, and scalability. We significantly reduce the linearizing quality gap and produce state-of-the-art subquadratic LLMs from Llama 3 8B and Mistral 7B v0.1, leading to 20+ points of improvement on 5-shot MMLU. Furthermore, LoLCATs does so with only 0.2% of past methods' model parameters and 0.04-0.2% of their training tokens. Finally, we apply LoLCATs to create the first linearized 70B and 405B LLMs (50$\times$ that of prior work). When compared with prior approaches under the same compute budgets, LoLCATs significantly improves linearizing quality, closing the gap between linearized and original Llama 3.1 70B and 405B LLMs by 77.8\% and 78.1\% on 5-shot MMLU.

Training Large Language Models (LLMs) presents a significant communication bottleneck, predominantly due to the growing scale of the gradient to communicate across multi-device clusters. However, how to mitigate communication overhead in practice remains a formidable challenge due to the weakness of the methodology of the existing compression methods, especially the neglect of the characteristics of the gradient. In this paper, we consider and demonstrate the low-rank properties of gradient and Hessian observed in LLMs training dynamic, and take advantage of such natural properties to design SEPARATE, a simple low-rank projection for gradient compression in modern large-scale model training processes. SEPARATE realizes dimensional reduction by common random Gaussian variables and an improved moving average error-feedback technique. We theoretically demonstrate that SEPARATE-based optimizers maintain the original convergence rate for SGD and Adam-Type optimizers for general non-convex objectives. Experimental results show that SEPARATE accelerates training speed by up to 2× for GPT-2-Medium pre-training, and improves performance on various benchmarks for LLAMA2-7B fine-tuning.

Rank collapse, a phenomenon where embedding vectors in sequence models rapidly converge to a uniform token or equilibrium state, has recently gained at- tention in the deep learning literature. This phenomenon leads to reduced expres- sivity and potential training instabilities due to vanishing gradients. Empirical ev- idence suggests that architectural components like skip connections, LayerNorm, and MultiLayer Perceptrons (MLPs) play critical roles in mitigating rank collapse. While this issue is well-documented for transformers, alternative sequence mod- els, such as State Space Models (SSMs), which have recently gained prominence, have not been thoroughly examined for similar vulnerabilities. This paper extends the theory of rank collapse from transformers to SSMs using a unifying frame- work that captures both architectures. We introduce a modification in the skip connection component, termed lambda-skip connections, that provides guaran- tees for rank collapse prevention. We present, via analytical results, a sufficient condition to achieve the guarantee for all of the aforementioned architectures. We also study the necessity of this condition via ablation studies and analytical exam- ples. To our knowledge, this is the first study that provides a general guarantee to prevent rank collapse, and that investigates rank collapse in the context of SSMs, offering valuable understanding for both theoreticians and practitioners. Finally, we validate our findings with experiments demonstrating the crucial role of archi- tectural components in preventing rank collapse.