Study algebraic invariants from lightning self-attention models.
problem Understanding polynomial coefficients of self-attention mechanisms.
method Identify algebraic invariants using polynomial coefficients and coordinate geometry.
result Found linear and nonlinear families of algebraic invariants.
GCL-LRR improves node classification in noisy graphs.
problem Noise in real-world graph data impairs GNNs' effectiveness.
method Two-stage transductive learning with low-rank regularization and attention.
result Improved node classification performance in noisy graphs.
This paper addresses the challenging task of video captioning which aims to generate descriptions for video data. Recently, the attention-based encoder-decoder structures have been widely used in video captioning. In existing literature, the attention weights are often built from the information of an individual modali…
New approach reduces model size for Transformer architectures.
problem Large embedding dimensions limit model applicability.
method Identified low-rank bottleneck in multi-head attention.
result Reducing head size to sequence length improves model performance.
A new model detects and localizes anomalies in multivariate time series data.
problem Anomaly diagnosis in multivariate time series data, especially localization.
method Attention Low-Rank Transformer (ALoRa-T) with low-rank regularization and Attention Low-Rank score.
result The proposed method significantly outperforms state-of-the-art methods in anomaly detection and localization.
LoLCATs improves linearized LLM quality with less memory and compute.
problem Linearizing large language models (LLMs) often degrades model quality and requires expensive training.
method Two-step method: attention transfer and low-rank adaptation.
result Significant improvement in linearizing quality with 20+ points on 5-shot MMLU.
Attention improves edge prediction in e-commerce graphs.
problem Predicting edges in graphs from node attributes in e-commerce.
method Used attention mechanism in simple feedforward networks, derived analytically tractable model AttEST.
result Attention network outperforms LSTM architectures by over 20% on F-1 score.
New insights into attention mechanisms reveal dramatic trade-offs between rank and heads.
problem Dramatic trade-offs between rank and number of heads in attention mechanisms.
method Presented a simple target function and proved theoretical limits.
result Full-rank attention is necessary for long contexts, while low-rank is sufficient for short ones.
This paper improves GNNs' generalization by adding a Low-Rank Global Attention module.
problem Improving the generalization power of Graph Neural Networks (GNNs).
method Incorporating a Low-Rank Global Attention (LRGA) module into GNNs.
result Augmenting GNNs with LRGA aligns them with a powerful graph isomorphism test, 2-Folklore Weisfeiler-Lehman (2-FWL).
A new method for efficient neural network fine-tuning using queryable low-rank update atoms.
problem Rigidity of static low-rank adaptation methods when input and depth-wise computation vary.
method A shared queryable memory of low-rank update atoms, allowing dynamic and context-sensitive adaptation.
result Improves final test performance and training stability compared to standard low-rank adaptation.
The study reveals the spectral structure of attention layers and its implications for generalization.
problem Understanding the spectral structure and generalization of trained attention layers.
method Empirical risk minimization in a single-head tied-attention layer, using random matrix theory, spin-glass theory, and approximate message passing.
result Exact high-dimensional characterization of training and test error, interpolation and recovery thresholds, and spectrum of the key and query matrices.
Low-rank modeling generally refers to a class of methods that solve problems by representing variables of interest as low-rank matrices. It has achieved great success in various fields including computer vision, data mining, signal processing and bioinformatics. Recently, much progress has been made in theories, algori…
We consider the problem of approximately reconstructing a partially-observed, approximately low-rank matrix. This problem has received much attention lately, mostly using the trace-norm as a surrogate to the rank. Here we study low-rank matrix reconstruction using both the trace-norm, as well as the less-studied max-no…
The problem of low-rank matrix estimation recently received a lot of attention due to challenging applications. A lot of work has been done on rank-penalized methods and convex relaxation, both on the theoretical and applied sides. However, only a few papers considered Bayesian estimation. In this paper, we review the …
Low-rank tensor regression, a new model class that learns high-order correlation from data, has recently received considerable attention. At the same time, Gaussian processes (GP) are well-studied machine learning models for structure learning. In this paper, we demonstrate interesting connections between the two, espe…
New online method for statistical inference with matrix context in decision-making.
problem Statistical inference in decision-making with matrix context.
method Proposes a fully online procedure to conduct statistical inference with adaptive data collection, handling low-rank structure.
result Establishes asymptotic normality of debiased estimators and proves validity of confidence intervals.
Matrices of (approximate) low rank are pervasive in data science, appearing in recommender systems, movie preferences, topic models, medical records, and genomics. While there is a vast literature on how to exploit low rank structure in these datasets, there is less attention on explaining why the low rank structure ap…
Survey on factor models and their applications in econometrics.
problem Estimating low-rank structures in high-dimensional models.
method Low-rank recovery techniques for factor model estimation.
result New insights into factor model applications in econometrics.
New method reduces summary points for datasets while maintaining quality.
problem Thinning datasets to reduce summary points while maintaining quality.
method Low-rank analysis of sub-Gaussian thinning.
result Guarantees high-quality compression for any distribution and kernel.
Linformer reduces transformer complexity to linear, improving efficiency.
problem High cost of training and deploying large transformer models for long sequences.
method Approximates self-attention with low-rank matrix, proposing Linformer with O(n) complexity. result Linformer performs similarly to standard transformers but is more memory- and time-efficient.
Transformers with linear space and time complexity for accurate attention estimation.
problem Efficiently estimating attention in large-scale tasks without relying on priors.
method Performers use Fast Attention Via positive Orthogonal Random features (FAVOR+) for linear approximation of softmax attention.
result Performers achieve competitive results on various tasks, demonstrating the effectiveness of their attention-learning approach.
LoRA fine-tuning causes forgetting, studied via particle system dynamics.
problem Catastrophic forgetting in LoRA fine-tuning.
method Mean-field self-attention model, partial differential equations, dynamical systems.
result Characterization of phase transitions in forgetting behavior.
Transformers can interpolate finite input sequences exactly.
problem Interpolating finite input sequences of arbitrary lengths.
method Constructing a transformer with alternating feed-forward and self-attention layers, and low-rank parameter matrices.
result Exact interpolation of datasets of finite input sequences in R^d with corresponding output sequences of smaller or equal length.
Low-rank modeling plays a pivotal role in signal processing and machine learning, with applications ranging from collaborative filtering, video surveillance, medical imaging, to dimensionality reduction and adaptive filtering. Many modern high-dimensional data and interactions thereof can be modeled as lying approximat…
S3Attention improves long sequence attention with smoothed skeleton sketching.
problem Quadratic complexity of vanilla Attention makes it unsuitable for long sequence tasks.
method S3Attention uses smoothing and matrix sketching to balance information preservation and computation. result S3Attention significantly outperforms vanilla Attention and other Attention variants. Tensor decomposition on big data has attracted significant attention recently. Among the most popular methods is a class of algorithms that leverages compression in order to reduce the size of the tensor and potentially parallelize computations. A fundamental requirement for such methods to work properly is that the lo…
OSA overcomes instability in skipless Transformers.
problem Instability in skipless Transformers using Softmax Self-Attention.
method OSA parametrizes attention matrix to be orthogonal via skew-symmetric matrix exponential.
result OSA allows for training non-causal Transformers without skip connections and normalisation layers.
Gated attention improves performance by using a hierarchical mixture of experts.
problem Improving performance of self-attention mechanisms in Transformers.
method Rigorously show that gated attention can be modeled as a hierarchical mixture of experts, providing a theoretical justification for its benefits.
result Gated attention is more sample-efficient than multi-head self-attention, requiring fewer data points to achieve the same estimation error.
In the past decade, sparse and low-rank recovery have drawn much attention in many areas such as signal/image processing, statistics, bioinformatics and machine learning. To achieve sparsity and/or low-rankness inducing, the ℓ1 norm and nuclear norm are of the most popular regularization penalties due to their co…
We analyze the computational limits of LoRA for transformer models using fine-grained complexity theory.
problem Computational efficiency of LoRA fine-tuning for transformer models.
method Fine-grained complexity theory, identifying phase transitions, almost linear algorithms.
result Existence of almost linear algorithms for LoRA adaptation based on specific norms.
This work introduces 'Artificial Entanglement' to understand LLMs' fine-tuning effectiveness.
problem Understanding the effectiveness of parameter-efficient fine-tuning methods for large language models.
method Adopting a quantum-information-inspired perspective, the study measures 'Artificial Entanglement' in neural networks.
result LoRA and FFT induce distinct internal entanglement signatures but not external ones, suggesting a 'no-hair' property.
We study gradient compression methods to alleviate the communication bottleneck in data-parallel distributed optimization. Despite the significant attention received, current compression schemes either do not scale well or fail to achieve the target test accuracy. We propose a new low-rank gradient compressor based on …
Enhances stock movement prediction using Higher Order Transformers for multimodal time-series data.
problem Predicting stock movements in financial markets with complex dynamics.
method Introduced Higher Order Transformers, extending self-attention and transformer architecture to capture complex market dynamics. Employed low-rank tensor decomposition and kernel attention to manage computational complexity. Integrated technical and fundamental analysis from historical prices and tweets.
result Demonstrated effectiveness of the method on the Stocknet dataset, improving stock movement prediction.
New method improves matrix completion accuracy, especially in noisy data.
problem Noisy matrix completion in recommendation systems and signal processing.
method Residual Spectral Matching criterion and pseudo-gradient algorithms.
result Improved numerical performance in noisy data environments.
In this article, we develop methods for estimating a low rank tensor from noisy observations on a subset of its entries to achieve both statistical and computational efficiencies. There have been a lot of recent interests in this problem of noisy tensor completion. Much of the attention has been focused on the fundamen…
Low rank tensor learning, such as tensor completion and multilinear multitask learning, has received much attention in recent years. In this paper, we propose higher order matching pursuit for low rank tensor learning problems with a convex or a nonconvex cost function, which is a generalization of the matching pursuit…
Determinantal point processes (DPPs) have garnered attention as an elegant probabilistic model of set diversity. They are useful for a number of subset selection tasks, including product recommendation. DPPs are parametrized by a positive semi-definite kernel matrix. In this work we present a new method for learning th…
LOT improves optimal transport for large datasets.
problem Efficient optimal transport for large datasets.
method Low-rank optimal transport (LOT) restricts search to low-nonnegative rank couplings.
result LOT complements and improves upon entropic regularization.
Particles representing tokens cluster in Transformers, influenced by initial tokens and matrix spectrum.
problem Understanding the geometry of learned representations in Transformers.
method Viewing Transformers as particle systems, applying dynamical systems and partial differential equations.
result Particles cluster towards limiting objects, confirming context-awareness and the emergence of leaders.
Meta learns low-rank covariance factors for better uncertainty estimation.
problem Sub-optimal covariance matrices in multi-task settings.
method Meta learns diagonal or diagonal plus low-rank factors using an attentive set encoder.
result Efficiently constructed task-specific covariance matrices improve uncertainty estimation.
Robust principal component analysis (RPCA) has drawn significant attentions due to its powerful capability in recovering low-rank matrices as well as successful appplications in various real world problems. The current state-of-the-art algorithms usually need to solve singular value decomposition of large matrices, whi…
This work analyzes how transformers learn common linear regression tasks.
problem Understanding how in-context learning operates in real-world applications with common task structures.
method Analyzing a linear attention model trained on low-rank regression tasks.
result Statistical fluctuations in finite pre-training data induce an implicit regularization, leading to a sharp phase transition in generalization error.
New method enhances model fine-tuning with minimal data.
problem Improving model performance on new tasks with limited data.
method Introducing α-LoRA, a reparameterization method for fine-tuning. result Enhanced generalization ability of fine-tuned models.
Iterative AutoML improves ASR model compression by 5x without WER degradation.
problem Challenges in achieving high compression levels without degrading ASR performance.
method Iterative AutoML-based Low Rank Factorization (LRF) approach.
result Achieved over 5x compression without WER degradation.
RieCUR improves Robust PCA by combining Riemannian optimization and CUR decompositions.
problem Robust Principal Component Analysis (PCA) to recover low-rank and sparse matrices from their sum.
method Riemannian CUR (RieCUR) algorithm that combines Riemannian optimization and robust CUR decompositions.
result RieCUR achieves state-of-the-art performance in Robust PCA with improved robustness to outliers and comparable computational complexity.
In many applications that require matrix solutions of minimal rank, the underlying cost function is non-convex leading to an intractable, NP-hard optimization problem. Consequently, the convex nuclear norm is frequently used as a surrogate penalty term for matrix rank. The problem is that in many practical scenarios th…
In many applications that require matrix solutions of minimal rank, the underlying cost function is non-convex leading to an intractable, NP-hard optimization problem. Consequently, the convex nuclear norm is frequently used as a surrogate penalty term for matrix rank. The problem is that in many practical scenarios th…
This work provides a guaranteed tensor recovery method by combining low-rankness and smoothness priors.
problem Guaranteed tensor recovery with theoretical guarantees for low-rank and smoothness priors.
method Developed a new regularization term that combines low-rankness and smoothness priors, proving exact recovery guarantees.
result Rigorously proved exact recovery guarantees for tensor completion and tensor robust principal component analysis.