Refine
Document Type
- Conference Proceeding (4)
- Doctoral Thesis (1)
- Article (unreviewed) (1)
Conference Type
- Konferenzartikel (4)
Language
- English (6)
Has Fulltext
- no (6)
Is part of the Bibliography
- yes (6)
Keywords
- Deep learning (1)
- Eigenvalues (1)
- Generative Adversarial Network (1)
- Mode Collapse (1)
- Neural Architecture Search (1)
- Optimization (1)
- Second-order Optimization (1)
- Stability (1)
- autoML (1)
- deep learning (1)
Institute
- IMLA - Institute for Machine Learning and Analytics (6) (remove)
Open Access
- Open Access (5)
- Bronze (1)
- Closed Access (1)
- Diamond (1)
Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss surface through its Hessian eigenvalues, and show that mode collapse is related to the convergence towards sharp minima. In particular, we observe how the eigenvalues of the G are directly correlated with the occurrence of mode collapse. Finally, motivated by these findings, we design a new optimization algorithm called nudged-Adam (NuGAN) that uses spectral information to overcome mode collapse, leading to empirically more stable convergence properties.
Due to its performance, the field of deep learning has gained a lot of attention, with neural networks succeeding in areas like Computer Vision (CV), Neural Language Processing (NLP), and Reinforcement Learning (RL). However, high accuracy comes at a computational cost as larger networks require longer training time and no longer fit onto a single GPU. To reduce training costs, researchers are looking into the dynamics of different optimizers, in order to find ways to make training more efficient. Resource requirements can be limited by reducing model size during training or designing more efficient models that improve accuracy without increasing network size.
This thesis combines eigenvalue computation and high-dimensional loss surface visualization to study different optimizers and deep neural network models. Eigenvectors of different eigenvalues are computed, and the loss landscape and optimizer trajectory are projected onto the plane spanned by those eigenvectors. A new parallelization method for the stochastic Lanczos method is introduced, resulting in faster computation and thus enabling high-resolution videos of the trajectory and secondorder information during neural network training. Additionally, the thesis presents the loss landscape between two minima along with the eigenvalue density spectrum at intermediate points for the first time.
Secondly, this thesis presents a regularization method for Generative Adversarial Networks (GANs) that uses second-order information. The gradient during training is modified by subtracting the eigenvector direction of the biggest eigenvalue, preventing the network from falling into the steepest minima and avoiding mode collapse. The thesis also shows the full eigenvalue density spectra of GANs during training.
Thirdly, this thesis introduces ProxSGD, a proximal algorithm for neural network training that guarantees convergence to a stationary point and unifies multiple popular optimizers. Proximal gradients are used to find a closed-form solution to the problem of training neural networks with smooth and non-smooth regularizations, resulting in better sparsity and more efficient optimization. Experiments show that ProxSGD can find sparser networks while reaching the same accuracy as popular optimizers.
Lastly, this thesis unifies sparsity and neural architecture search (NAS) through the framework of group sparsity. Group sparsity is achieved through ℓ2,1-regularization during training, allowing for filter and operation pruning to reduce model size with minimal sacrifice in accuracy. By grouping multiple operations together, group sparsity can be used for NAS as well. This approach is shown to be more robust while still achieving competitive accuracies compared to state-of-the-art methods
In this paper, we propose a unified approach for network pruning and one-shot neural architecture search (NAS) via group sparsity. We first show that group sparsity via the recent Proximal Stochastic Gradient Descent (ProxSGD) algorithm achieves new state-of-the-art results for filter pruning. Then, we extend this approach to operation pruning, directly yielding a gradient-based NAS method based on group sparsity. Compared to existing gradient-based algorithms such as DARTS, the advantages of this new group sparsity approach are threefold. Firstly, instead of a costly bilevel optimization problem, we formulate the NAS problem as a single-level optimization problem, which can be optimally and efficiently solved using ProxSGD with convergence guarantees. Secondly, due to the operation-level sparsity, discretizing the network architecture by pruning less important operations can be safely done without any performance degradation. Thirdly, the proposed approach finds architectures that are both stable and well-performing on a variety of search spaces and datasets.
Correlation Clustering, also called the minimum cost Multicut problem, is the process of grouping data by pairwise similarities. It has proven to be effective on clustering problems, where the number of classes is unknown. However, not only is the Multicut problem NP-hard, an undirected graph G with n vertices representing single images has at most edges, thus making it challenging to implement correlation clustering for large datasets. In this work, we propose Multi-Stage Multicuts (MSM) as a scalable approach for image clustering. Specifically, we solve minimum cost Multicut problems across multiple distributed compute units. Our approach not only allows to solve problem instances which are too large to fit into the shared memory of a single compute node, but it also achieves significant speedups while preserving the clustering accuracy at the same time. We evaluate our proposed method on the CIFAR10 …
We demonstrate how to exploit group sparsity in order to bridge the areas of network pruning and neural architecture search (NAS). This results in a new one-shot NAS optimizer that casts the problem as a single-level optimization problem and does not suffer any performance degradation from discretizating the architecture.
Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss surface through its Hessian eigenvalues, and show that mode collapse is related to the convergence towards sharp minima. In particular, we observe how the eigenvalues of the are directly correlated with the occurrence of mode collapse. Finally, motivated by these findings, we design a new optimization algorithm called nudged-Adam (NuGAN) that uses spectral information to overcome mode collapse, leading to empirically more stable convergence properties.