Iteratively reweighted least square (IRLS) is a popular approach to solve sparsity-enforcing regression problems in machine learning. State of the art approaches are more efficient but typically rely on specific coordinate pruning schemes. In this work, we show how a surprisingly simple re-parametrization of IRLS, coupled with a bilevel resolution (instead of an alternating scheme) is able to achieve top performances on a wide range of sparsity (such as Lasso, group Lasso and trace norm regularizations), regularization strength (including hard constraints), and design matrices (ranging from correlated designs to differential operators). Similarly to IRLS, our method only involves linear systems resolutions, but in sharp contrast, corresponds to the minimization of a smooth function. Despite being non-convex, we show that there is no spurious minima and that saddle points are ridable'', so that there always exists a descent direction. We thus advocate for the use of a BFGS quasi-Newton solver, which makes our approach simple, robust and efficient. We perform a numerical benchmark of the convergence speed of our algorithm against state of the art solvers for Lasso, group Lasso, trace norm and linearly constrained problems. These results highlight the versatility of our approach, removing the need to use different solvers depending on the specificity of the ML problem under study.

In this paper, we investigate the use of small datasets in the context of offline reinforcement learning (RL). While many common offline RL benchmarks employ datasets with over a million data points, many offline RL applications rely on considerably smaller datasets. We show that offline RL algorithms can overfit on small datasets, resulting in poor performance. To address this challenge, we introduce "Sparse-Reg": a regularization technique based on sparsity to mitigate overfitting in offline reinforcement learning, enabling effective learning in limited data settings and outperforming state-of-the-art baselines in continuous control.

Iteratively reweighted least square (IRLS) is a popular approach to solve sparsity-enforcing regression problems in machine learning. State of the art approaches are more efficient but typically rely on specific coordinate pruning schemes. In this work, we show how a surprisingly simple re-parametrization of IRLS, coupled with a bilevel resolution (instead of an alternating scheme) is able to achieve top performances on a wide range of sparsity (such as Lasso, group Lasso and trace norm regularizations), regularization strength (including hard constraints), and design matrices (ranging from correlated designs to differential operators). Similarly to IRLS, our method only involves linear systems resolutions, but in sharp contrast, corresponds to the minimization of a smooth function. Despite being non-convex, we show that there is no spurious minima and that saddle points are "ridable'', so that there always exists a descent direction. We thus advocate for the use of a BFGS quasi-Newton solver, which makes our approach simple, robust and efficient.

Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational and storage costs. Modern pruning strategies employ one-shot techniques to compress PLMs without the need for retraining on task-specific or otherwise general data; however, these approaches often lead to an indispensable reduction in performance. In this paper, we propose SDS, a Sparse-Dense-Sparse pruning framework to enhance the performance of the pruned PLMs from a weight distribution optimization perspective. We outline the pruning process in three steps. Initially, we prune less critical connections in the model using conventional one-shot pruning methods. Next, we reconstruct a dense model featuring a pruning-friendly weight distribution by reactivating pruned connections with sparse regularization. Finally, we perform a second pruning round, yielding a superior pruned model compared to the initial pruning. Experimental results demonstrate that SDS outperforms the state-of-the-art pruning techniques SparseGPT and Wanda under an identical sparsity configuration. For instance, SDS reduces perplexity by 9.13 on Raw-Wikitext2 and improves accuracy by an average of 2.05% across multiple zero-shot benchmarks for OPT-125M with 2:4 sparsity.

We study learning formulations with non-convex regularizaton that are natural for sparse linear models. There are two approaches to this problem: (1) Heuristic methods such as gradient descent that only find a local minimum. A drawback of this approach is the lack of theoretical guarantee showing that the local minimum gives a good solution. However it often leads to sub-optimal sparsity in reality. This paper tries to remedy the above gap between theory and practice.

Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited in long utterances. Existing solutions either depend on increasing model complexity or try to balance between local features and global context to address this issue. To effectively leverage the long-term dependencies of audio signals and constrain model complexity, we introduce a novel module called Global-aware Filter layer (GF layer) in this work, which employs a set of learnable transform-domain filters between a 1D discrete Fourier transform and its inverse transform to capture global context. Additionally, we develop a dynamic filtering strategy and a sparse regularization method to enhance the performance of the GF layer and prevent overfitting. Based on the GF layer, we present a dual-stream TDNN architecture called DS-TDNN for automatic speaker verification (ASV), which utilizes two unique branches to extract both local and global features in parallel and employs an efficient strategy to fuse different-scale information. Experiments on the Voxceleb and SITW databases demonstrate that the DS-TDNN achieves a relative improvement of 10\% together with a relative decline of 20\% in computational cost over the ECAPA-TDNN in speaker verification task. This improvement will become more evident as the utterance's duration grows. Furthermore, the DS-TDNN also beats popular deep residual models and attention-based systems on utterances of arbitrary length.

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a substantial amount of training data still make Vision Transformers computationally burdensome. In this research, we investigate the possibility of applying Sparse Regularization to Vision Transformers and the impact of Pruning, either after Sparse Regularization or without it, on the trade-off between performance and efficiency. To accomplish this, we apply Sparse Regularization and Pruning methods to the Vision Transformer architecture for image classification tasks on the CIFAR-10, CIFAR-100, and ImageNet-100 datasets. The training process for the Vision Transformer model consists of two parts: pre-training and fine-tuning. Pre-training utilizes ImageNet21K data, followed by fine-tuning for 20 epochs. The results show that when testing with CIFAR-100 and ImageNet-100 data, models with Sparse Regularization can increase accuracy by 0.12%. Furthermore, applying pruning to models with Sparse Regularization yields even better results. Specifically, it increases the average accuracy by 0.568% on CIFAR-10 data, 1.764% on CIFAR-100, and 0.256% on ImageNet-100 data compared to pruning models without Sparse Regularization. Code can be accesed here: https://github.com/yogiprsty/Sparse-ViT

Differentiable architecture search (DARTS) is a promising end to end NAS method which directly optimizes the architecture parameters through general gradient descent. However, DARTS is brittle to the catastrophic failure incurred by the skip connection in the search space. Recent studies also cast doubt on the basic underlying hypotheses of DARTS which are argued to be inherently prone to the performance discrepancy between the continuous-relaxed supernet in the training phase and the discretized finalnet in the evaluation phase. We figure out that the robustness problem and the skepticism can both be explained by the information bypass leakage during the training of the supernet. This naturally highlights the vital role of the sparsity of architecture parameters in the training phase which has not been well developed in the past. We thus propose a novel sparse-regularized approximation and an efficient mixed-sparsity training scheme to robustify DARTS by eliminating the information bypass leakage. We subsequently conduct extensive experiments on multiple search spaces to demonstrate the effectiveness of our method.

More competent learning models are demanded for data processing due to increasingly greater amounts of data available in applications. Data that we encounter often have certain embedded sparsity structures. That is, if they are represented in an appropriate basis, their energies can concentrate on a small number of basis functions. This paper is devoted to a numerical study of adaptive approximation of solutions of nonlinear partial differential equations whose solutions may have singularities, by deep neural networks (DNNs) with a sparse regularization with multiple parameters. Noting that DNNs have an intrinsic multi-scale structure which is favorable for adaptive representation of functions, by employing a penalty with multiple parameters, we develop DNNs with a multi-scale sparse regularization (SDNN) for effectively representing functions having certain singularities. We then apply the proposed SDNN to numerical solutions of the Burgers equation and the Schr\"odinger equation. Numerical examples confirm that solutions generated by the proposed SDNN are sparse and accurate.

Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks (CNNs) by pruning the filters of less importance to the final output accuracy. To reduce the degradation of performance after pruning, many methods utilize the loss with sparse regularization to produce structured sparsity. In this paper, we analyze these sparsity-training-based methods and find that the regularization of unpruned channels is unnecessary. Moreover, it restricts the network's capacity, which leads to under-fitting. To solve this problem, we propose a novel pruning method, named MaskSparsity, with pruning-aware sparse regularization. MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model. Before the fine-grained sparse regularization of MaskSparity, we can use many methods to get the pruning mask, such as running the global sparse regularization. MaskSparsity achieves 63.03%-FLOPs reduction on ResNet-110 by removing 60.34% of the parameters, with no top-1 accuracy loss on CIFAR-10. On ILSVRC-2012, MaskSparsity reduces more than 51.07% FLOPs on ResNet-50, with only a loss of 0.76% in the top-1 accuracy. The code is released at https://github.com/CASIA-IVA-Lab/MaskSparsity. Moreover, we have integrated the code of MaskSparity into a PyTorch pruning toolkit, EasyPruner, at https://gitee.com/casia_iva_engineer/easypruner.