Implicit neural networks have demonstrated remarkable success in various
tasks. However, there is a lack of theoretical analysis of the connections and
differences between implicit and explicit networks. In this paper, we study
high-dimensional implicit neural networks and provide the high dimensional
equivalents for the corresponding conjugate kernels and neural tangent kernels.
Built upon this, we establish the equivalence between implicit and explicit
networks in high dimensions.

高维隐式神经网络的理论分析与显式网络之间的联系和差异，构建了对应共轭核和神经切向核的高维等价关系，从而在高维空间中建立了隐式与显式网络之间的等价性。

隐式神经网络与显式神经网络的等效性：一个高维视角

On the Equivalence between Implicit and Explicit Neural Networks: A  High-dimensional Viewpoint

We propose a linguistic interpretation of three-way decisions, where the
regions of acceptance, rejection, and non-commitment are constructed by using
the so-called evaluative linguistic expressions, which are expressions of
natural language such as small, medium, very short, quite roughly strong,
extremely good, etc. Our results highlight new connections between two
different research areas: three-way decisions and the theory of evaluative
linguistic expressions.

我们提出了一种关于三态决策的语言解释，用所谓的评价性语言表达构建了接受、拒绝和不作为的区域，这些表达是自然语言中的表达，比如小的、中等的、非常短的、相当粗糙的、极好的等。我们的研究结果强调了三态决策和评价性语言表达理论之间的新联系。

具有评价语言表达的三方式决策

Three-way Decisions with Evaluative Linguistic Expressions

Delta tuning (DET, also known as parameter-efficient tuning) is deemed as the
new paradigm for using pre-trained language models (PLMs). Up to now, various
DETs with distinct design elements have been proposed, achieving performance on
par with fine-tuning. However, the mechanisms behind the above success are
still under-explored, especially the connections among various DETs. To fathom
the mystery, we hypothesize that the adaptations of different DETs could all be
reparameterized as low-dimensional optimizations in a unified optimization
subspace, which could be found by jointly decomposing independent solutions of
different DETs. Then we explore the connections among different DETs by
conducting optimization within the subspace. In experiments, we find that, for
a certain DET, conducting optimization simply in the subspace could achieve
comparable performance to its original space, and the found solution in the
subspace could be transferred to another DET and achieve non-trivial
performance. We also visualize the performance landscape of the subspace and
find that there exists a substantial region where different DETs all perform
well. Finally, we extend our analysis and show the strong connections between
fine-tuning and DETs.

通过研究 Delta tuning 的最新模型，我们提出一种用于连接不同模型的统一优化子空间的低维优化参数的假设，并通过研究不同模型之间的关联性，探究这一假设。我们发现，在这个假设下，不同的 Delta tuning 可以实现互相转移，并且在统一优化子空间中的性能显著。最后，我们证明了精调与 Delta tuning 之间的强关联性。

不同曲调同等技巧演奏：探索一个用于 Delta 调制的统一优化子空间

Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning

This short article revisits some of the ideas introduced in arXiv:1701.07875
and arXiv:1705.07642 in a simple setup. This sheds some lights on the
connexions between Variational Autoencoders (VAE), Generative Adversarial
Networks (GAN) and Minimum Kantorovitch Estimators (MKE).

该研究简述了 Variational Autoencoders（VAE）、Generative Adversarial Networks（GAN）和 Minimum Kantorovitch Estimators（MKE）三者之间的联系及其研究领域。