Einsum expressions specify an output tensor in terms of several input tensors. They offer a simple yet expressive abstraction for many computational tasks in artificial intelligence and beyond. However, evaluating einsum expressions poses hard algorithmic problems that depend on the representation of the tensors. Two popular representations are multidimensional arrays and coordinate lists. The latter is a more compact representation for sparse tensors, that is, tensors where a significant proportion of the entries are zero. So far, however, most of the popular einsum implementations use the multidimensional array representation for tensors. Here, we show on a non-trivial example that, when evaluating einsum expressions, coordinate lists can be exponentially more efficient than multidimensional arrays. In practice, however, coordinate lists can also be significantly less efficient than multidimensional arrays, but it is hard to decide from the input tensors whether this will be the case.

Linear Mode Connectivity (LMC) is a notable phenomenon in the loss landscapes of neural networks, wherein independently trained models have been observed to be connected--up to permutation symmetries--by linear paths in parameter space along which the loss remains consistently low. This observation challenges classical views of non-convex optimization and has implications for model ensembling, generalization, and our understanding of neural loss geometry. Inspired by recent studies on LMC in standard neural networks, we systematically investigate this phenomenon within Mixture-of-Experts (MoE) architectures--a class of models known for their scalability and computational efficiency, which combine traditional neural networks--referred to as experts--through a learnable gating mechanism. We begin by conducting a comprehensive analysis of both dense and sparse gating regimes, demonstrating that the symmetries inherent to MoE architectures are fully characterized by permutations acting on both the expert components and the gating function. Building on these foundational findings, we propose a matching algorithm that enables alignment between independently trained MoEs, thereby facilitating the discovery of LMC. Finally, we empirically validate the presence of LMC using our proposed algorithm across diverse MoE configurations--including dense, sparse, and shared-expert variants--under a wide range of model settings and datasets of varying scales and modalities. Our results confirm the existence of LMC in MoE architectures and offer fundamental insights into the functional landscape and optimization dynamics of deep learning models.

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of gating. In this work, we conduct comprehensive experiments to systematically investigate gating-augmented softmax attention variants. Specifically, we perform a comprehensive comparison over 30 variants of 15B Mixture-of-Experts (MoE) models and 1.7B dense models trained on a 3.5 trillion token dataset. Our central finding is that a simple modification--applying a head-specific sigmoid gate after the Scaled Dot-Product Attention (SDPA)--consistently improves performance. This modification also enhances training stability, tolerates larger learning rates, and improves scaling properties. By comparing various gating positions and computational variants, we attribute this effectiveness to two key factors: (1) introducing non-linearity upon the low-rank mapping in the softmax attention, and (2) applying query-dependent sparse gating scores to modulate the SDPA output. Notably, we find this sparse gating mechanism mitigates, and enhances long-context extrapolation performance. We also release related codes (https://github.com/qiuzh20/gated

Recent advances in AI, driven by Transformer architectures, have achieved remarkable success in language, vision, and multimodal reasoning, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target problems by inferring compositional rules from context examples, which are composed of basic components structured by underlying rules. However, some of these tasks remain challenging for Transformers, which are not inherently designed to handle compositional tasks and offer limited structural inductive bias. Inspired by sparse coding, we propose a reformulation of the attention to enhance its capability for compositional tasks. In sparse coding, data are represented as sparse combinations of basic elements, with the resulting coefficients capturing the underlying compositional structure of the input.

In this section, we provide a convergence rate analysis for Algorithm 1. Similar to Hazan et al. [36], Algorithm 1 has access to an approximate density oracle and an approximate planner defined below: Visitation density oracle: We assume access to an approximate density estimator that takes in a policy and a density approximation error d 0 as inputs and returns ˆd such that kd ˆd k1 d. Approximate planning oracle: We assume access to an approximate planner that, given any MDP M and error tolerance p 0, returns a policy such that JM() max JM() p. A.1 Proof of Theorem 1 We first give the following proposition that captures certain properties of the proposed objective. The proof is postponed to the end of this section. Taking the above proposition as given for the moment, we prove Theorem 1 following steps similar to those of Hazan et al. [36, Theorem 4.1]. Since k returned by the approximate planning oracle is an p-optimal policy in Mk, we have (1) 1hd k,rki (1) 1hd,rki p for any policy, including?. Therefore, It is straightforward to check that setting 0.1 1, p 0.1, d 0.1 1, 0.1, and the number of iterations K 1 log(10B 1) yields the claim of Theorem 1. Remark 2. Since the temperature parameter k in Proposition 1 goes to zero as k increases, one can show that the expected value of policy returned by Algorithm 1 converges to the maximum performance J(?).

We adopt a residual network (ResNet) [23] based feature extractor, with ELU as the activation function. Following [15], we adopt group normalization and instance normalization for better stability of the networks. We adopt the "leave-one-out" training strategy for obtaining the results on each of the categories of MVTec-AD. All experiments are performed with the same settings and hyperparameters. We resize all images to 128 128, and do not perform any data augmentation.

Improving the performance of deep networks in data-limited regimes has warranted much attention. In this work, we empirically show that "winning tickets" (small subnetworks) obtained via magnitude pruning based on the lottery ticket hypothesis [1], apart from being sparse are also effective recognizers in data-limited regimes. Based on extensive experiments, we find that in low data regimes (datasets of 50-100 examples per class), sparse winning tickets substantially outperform the original dense networks. This approach, when combined with augmentations or fine-tuning from a self-supervised backbone network, shows further improvements in performance by as much as 16% (absolute) on low sample datasets and longtailed classification. Further, sparse winning tickets are more robust to synthetic noise and distribution shifts compared to their dense counterparts. Our analysis of winning tickets on small datasets indicates that, though sparse, the networks retain density in the initial layers and their representations are more generalizable.

Probabilistic inference serves as a popular model for neural processing. It is still unclear, however, how approximate probabilistic inference can be accurate and scalable to very high-dimensional continuous latent spaces. Especially as typical posteriors for sensory data can be expected to exhibit complex latent dependencies including multiple modes. Here, we study an approach that can efficiently be scaled while maintaining a richly structured posterior approximation under these conditions. As example model we use spike-and-slab sparse coding for V1 processing, and combine latent subspace selection with Gibbs sampling (selectand-sample).

In this paper we present a practical solution with performance guarantees to the problem of dimensionality reduction for very large scale sparse matrices. We show applications of our approach to computing the Principle Component Analysis (PCA) of any n dmatrix, using one pass over the stream of its rows. Our solution uses coresets: a scaled subset of the n rows that approximates their sum of squared distances to every k-dimensional affine subspace. An open theoretical problem has been to compute such a coreset that is independent of both n and d. An open practical problem has been to compute a non-trivial approximation to the PCA of very large but sparse databases such as the Wikipedia document-term matrix in a reasonable time. We answer both of these questions affirmatively. Our main technical result is a new framework for deterministic coreset constructions based on a reduction to the problem of counting items in a stream.