Searcharxiv⌕ Search

arXiv subjects

Clayton Sanford

Publications and source records attributed to Clayton Sanford.

At least 19 recordsLinked to original sources
arXiv2026

Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers

Transformers have become a central architecture for graph learning, but their application to graphs requires first choosing a tokenization: a graph-to-token map that determines which structural information is exposed at the input. In this work, we show that this choice is a fundamental component of transformer expressivity. We examine three tokenizations that serve as building blocks for many existing graph tokenizations: spectral, random-walk, and adjacency tokenizations. We prove that different tokenizations induce distinct depth regimes: the same graph computation may be realizable by a shallow transformer under one tokenization, while requiring substantially larger depth under another. For example, we prove that random-walk tokenization is lossy for any walk length, making it impossible in general to recover the graph from it, and that while spectral tokenization is lossless, it is ill-conditioned for local tasks. We further show that although both random-walk and spectral tokenizations are derived from adjacency information, it is impossible for a limited-depth transformer to convert between tokenization families in general. In particular, we establish lower bounds and impossibility results showing that unfavorable tokenizations may preclude the efficient recovery of more suitable structural representations. Finally, we complement our theory with controlled experiments on synthetic and real-world tasks, validating the predicted separations and showing that different tasks favor different structural views, and combining complementary tokenizations allows the transformer to leverage distinct signals from each representation.

cs.LG↗
arXiv2026

Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers

Transformers have revolutionized the field of machine learning. In particular, they can be used to solve complex algorithmic problems, including graph-based tasks. In such algorithmic tasks a key question is what is the minimal size of a transformer that can implement the task. Recent work has begun to explore this problem for graph-based tasks, showing that for sub-linear embedding dimension (i.e., model width) logarithmic depth suffices. However, an open question, which we address here, is what happens if width is allowed to grow linearly, while depth is kept fixed. Here we analyze this setting, and provide the surprising result that with linear width, constant depth suffices for solving a host of graph-based problems. This suggests that a moderate increase in width can allow much shallower models, which are advantageous in terms of inference and train time. For other problems, we show that quadratic width is required. Our results demonstrate the complex and intriguing landscape of transformer implementations of graph-based algorithms. We empirically investigate these trade-offs between the relative powers of depth and width and find tasks where wider models have the same accuracy as deep models, while having much faster train and inference time due to parallelizable hardware.

cs.LG↗
arXiv2026

Next-Token Prediction and Regret Minimization

We consider the question of how to employ next-token prediction algorithms in adversarial online decision-making environments. Specifically, if we train a next-token prediction model on a distribution $\mathcal{D}$ over sequences of opponent actions, when is it the case that the induced online decision-making algorithm (by approximately best responding to the model's predictions) has low adversarial regret (i.e., when is $\mathcal{D}$ a \emph{low-regret distribution})? For unbounded context windows (where the prediction made by the model can depend on all the actions taken by the adversary thus far), we show that although not every distribution $\mathcal{D}$ is a low-regret distribution, every distribution $\mathcal{D}$ is exponentially close (in TV distance) to one low-regret distribution, and hence sublinear regret can always be achieved at negligible cost to the accuracy of the original next-token prediction model. In contrast to this, for bounded context windows (where the prediction made by the model can depend only on the past $w$ actions taken by the adversary, as may be the case in modern transformer architectures), we show that there are some distributions $\mathcal{D}$ of opponent play that are $Θ(1)$-far from any low-regret distribution $\mathcal{D'}$ (even when $w = Ω(T)$ and such distributions exist). Finally, we complement these results by showing that the unbounded context robustification procedure can be implemented by layers of a standard transformer architecture, and provide empirical evidence that transformer models can be efficiently trained to represent these new low-regret distributions.

cs.LG↗
arXiv2025

Fast attention mechanisms: a tale of parallelism

Transformers have the representational capacity to simulate Massively Parallel Computation (MPC) algorithms, but they suffer from quadratic time complexity, which severely limits their scalability. We introduce an efficient attention mechanism called Approximate Nearest Neighbor Attention (ANNA) with sub-quadratic time complexity. We prove that ANNA-transformers (1) retain the expressive power previously established for standard attention in terms of matching the capabilities of MPC algorithms, and (2) can solve key reasoning tasks such as Match2 and $k$-hop with near-optimal depth. Using the MPC framework, we further prove that constant-depth ANNA-transformers can simulate constant-depth low-rank transformers, thereby providing a unified way to reason about a broad class of efficient attention approximations.

cs.LG↗
arXiv2025

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective

Theoretical efforts to prove advantages of Transformers in comparison with classical architectures such as feedforward and recurrent neural networks have mostly focused on representational power. In this work, we take an alternative perspective and prove that even with infinite compute, feedforward and recurrent networks may suffer from larger sample complexity compared to Transformers, as the latter can adapt to a form of dynamic sparsity. Specifically, we consider a sequence-to-sequence data generating model on sequences of length $N$, in which the output at each position depends only on $q$ relevant tokens with $q \ll N$, and the positions of these tokens are described in the input prompt. We prove that a single-layer Transformer can learn this model if and only if its number of attention heads is at least $q$, in which case it achieves a sample complexity almost independent of $N$, while recurrent networks require $N^{Ω(1)}$ samples on the same problem. If we simplify this model, recurrent networks may achieve a complexity almost independent of $N$, while feedforward networks still require $N$ samples. Consequently, our proposed sparse retrieval model illustrates a natural hierarchy in sample complexity across these architectures.

stat.ML↗
arXiv2024

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

Modern sequence models (e.g., Transformers, linear RNNs, etc.) emerged as dominant backbones of recent deep learning frameworks, mainly due to their efficiency, representational power, and/or ability to capture long-range dependencies. Adopting these sequence models for graph-structured data has recently gained popularity as the alternative to Message Passing Neural Networks (MPNNs). There is, however, a lack of a common foundation about what constitutes a good graph sequence model, and a mathematical description of the benefits and deficiencies in adopting different sequence models for learning on graphs. To this end, we first present Graph Sequence Model (GSM), a unifying framework for adopting sequence models for graphs, consisting of three main steps: (1) Tokenization, which translates the graph into a set of sequences; (2) Local Encoding, which encodes local neighborhoods around each node; and (3) Global Encoding, which employs a scalable sequence model to capture long-range dependencies within the sequences. This framework allows us to understand, evaluate, and compare the power of different sequence model backbones in graph tasks. Our theoretical evaluations of the representation power of Transformers and modern recurrent models through the lens of global and local graph tasks show that there are both negative and positive sides for both types of models. Building on this observation, we present GSM++, a fast hybrid model that uses the Hierarchical Affinity Clustering (HAC) algorithm to tokenize the graph into hierarchical sequences, and then employs a hybrid architecture of Transformer to encode these sequences. Our theoretical and experimental results support the design of GSM++, showing that GSM++ outperforms baselines in most benchmark evaluations.

cs.LG↗
arXiv2024

Understanding Transformer Reasoning Capabilities via Graph Algorithms

Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based neural networks, a theoretical understanding of their algorithmic reasoning capabilities in realistic parameter regimes is lacking. We investigate this question in terms of the network's depth, width, and number of extra tokens for algorithm execution. Our novel representational hierarchy separates 9 algorithmic reasoning problems into classes solvable by transformers in different realistic parameter scaling regimes. We prove that logarithmic depth is necessary and sufficient for tasks like graph connectivity, while single-layer transformers with small embedding dimensions can solve contextual retrieval tasks. We also support our theoretical analysis with ample empirical evidence using the GraphQA benchmark. These results show that transformers excel at many graph reasoning tasks, even outperforming specialized graph neural networks.

cs.LG↗
arXiv2024

Transformers, parallel computation, and logarithmic depth

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is sufficient for transformers to solve basic computational tasks that cannot be efficiently solved by several other neural sequence models and sub-quadratic transformer approximations. We thus establish parallelism as a key distinguishing property of transformers.

cs.LG↗
arXiv2023

Representational Strengths and Limitations of Transformers

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both positive and negative results on the representation power of attention layers, with a focus on intrinsic complexity parameters such as width, depth, and embedding dimension. On the positive side, we present a sparse averaging task, where recurrent networks and feedforward networks all have complexity scaling polynomially in the input size, whereas transformers scale merely logarithmically in the input size; furthermore, we use the same construction to show the necessity and role of a large embedding dimension in a transformer. On the negative side, we present a triple detection task, where attention layers in turn have complexity scaling linearly in the input size; as this scenario seems rare in practice, we also present natural variants that can be efficiently solved by attention layers. The proof techniques emphasize the value of communication complexity in the analysis of transformers and related models, and the role of sparse averaging as a prototypical attention task, which even finds use in the analysis of triple detection.

cs.LG↗
arXiv2023

Intrinsic dimensionality and generalization properties of the $\mathcal{R}$-norm inductive bias

We study the structural and statistical properties of $\mathcal{R}$-norm minimizing interpolants of datasets labeled by specific target functions. The $\mathcal{R}$-norm is the basis of an inductive bias for two-layer neural networks, recently introduced to capture the functional effect of controlling the size of network weights, independently of the network width. We find that these interpolants are intrinsically multivariate functions, even when there are ridge functions that fit the data, and also that the $\mathcal{R}$-norm inductive bias is not sufficient for achieving statistically optimal generalization for certain learning problems. Altogether, these results shed new light on an inductive bias that is connected to practical neural network training.

cs.LG↗
arXiv2022

Improving the predictions of ML-corrected climate models with novelty detection

While previous works have shown that machine learning (ML) can improve the prediction accuracy of coarse-grid climate models, these ML-augmented methods are more vulnerable to irregular inputs than the traditional physics-based models they rely on. Because ML-predicted corrections feed back into the climate model's base physics, the ML-corrected model regularly produces out of sample data, which can cause model instability and frequent crashes. This work shows that adding semi-supervised novelty detection to identify out-of-sample data and disable the ML-correction accordingly stabilizes simulations and sharply improves the quality of predictions. We design an augmented climate model with a one-class support vector machine (OCSVM) novelty detector that provides better temperature and precipitation forecasts in a year-long simulation than either a baseline (no-ML) or a standard ML-corrected run. By improving the accuracy of coarse-grid climate models, this work helps make accurate climate models accessible to researchers without massive computational resources.

physics.ao-ph↗
arXiv2022

Learning Single-Index Models with Shallow Neural Networks

Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input. These models are particularly relevant in high dimension, when the data might present low-dimensional structure that learning algorithms should adapt to. While several statistical aspects of this model, such as the sample complexity of recovering the relevant (one-dimensional) subspace, are well-understood, they rely on tailored algorithms that exploit the specific structure of the target function. In this work, we introduce a natural class of shallow neural networks and study its ability to learn single-index models via gradient flow. More precisely, we consider shallow networks in which biases of the neurons are frozen at random initialization. We show that the corresponding optimization landscape is benign, which in turn leads to generalization guarantees that match the near-optimal sample complexity of dedicated semi-parametric methods.

cs.LG↗
arXiv2022

On Scrambling Phenomena for Randomly Initialized Recurrent Networks

Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics, and their sensitivity to the initialization process often renders them notoriously hard to train. Recent works have shed light on such phenomena analyzing when exploding or vanishing gradients may occur, either of which is detrimental for training dynamics. In this paper, we point to a formal connection between RNNs and chaotic dynamical systems and prove a qualitatively stronger phenomenon about RNNs than what exploding gradients seem to suggest. Our main result proves that under standard initialization (e.g., He, Xavier etc.), RNNs will exhibit \textit{Li-Yorke chaos} with \textit{constant} probability \textit{independent} of the network's width. This explains the experimentally observed phenomenon of \textit{scrambling}, under which trajectories of nearby points may appear to be arbitrarily close during some timesteps, yet will be far away in future timesteps. In stark contrast to their feedforward counterparts, we show that chaotic behavior in RNNs is preserved under small perturbations and that their expressive power remains exponential in the number of feedback iterations. Our technical arguments rely on viewing RNNs as random walks under non-linear activations, and studying the existence of certain types of higher-order fixed points called \textit{periodic points} that lead to phase transitions from order to chaos.

cs.LG↗
arXiv2022

Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals

We consider the well-studied problem of learning intersections of halfspaces under the Gaussian distribution in the challenging \emph{agnostic learning} model. Recent work of Diakonikolas et al. (2021) shows that any Statistical Query (SQ) algorithm for agnostically learning the class of intersections of $k$ halfspaces over $\mathbb{R}^n$ to constant excess error either must make queries of tolerance at most $n^{-\tildeΩ(\sqrt{\log k})}$ or must make $2^{n^{Ω(1)}}$ queries. We strengthen this result by improving the tolerance requirement to $n^{-\tildeΩ(\log k)}$. This lower bound is essentially best possible since an SQ algorithm of Klivans et al. (2008) agnostically learns this class to any constant excess error using $n^{O(\log k)}$ queries of tolerance $n^{-O(\log k)}$. We prove two variants of our lower bound, each of which combines ingredients from Diakonikolas et al. (2021) with (an extension of) a different earlier approach for agnostic SQ lower bounds for the Boolean setting due to Dachman-Soled et al. (2014). Our approach also yields lower bounds for agnostically SQ learning the class of "convex subspace juntas" (studied by Vempala, 2010) and the class of sets with bounded Gaussian surface area; all of these lower bounds are nearly optimal since they essentially match known upper bounds from Klivans et al. (2008).

cs.LG↗
arXiv2021

Enabling equation-free modeling via diffusion maps

Equation-free modeling aims at extracting low-dimensional macroscopic dynamics from complex high-dimensional systems that govern the evolution of microscopic states. This algorithm relies on lifting and restriction operators that map macroscopic states to microscopic states and vice versa. Combined with simulations of the microscopic state, this algorithm can be used to apply Newton solvers to the implicitly defined low-dimensional macroscopic system or solve it more efficiently using direct numerical simulations. The key challenge is the construction of the lifting and restrictions operators that usually require a priori insight into the underlying application. In this paper, we design an application-independent algorithm that uses diffusion maps to construct these operators from simulation data. Code is available at https://doi.org/10.5281/zenodo.5793299.

math.DS↗
arXiv2021

Support vector machines and linear regression coincide with very high-dimensional features

The support vector machine (SVM) and minimum Euclidean norm least squares regression are two fundamentally different approaches to fitting linear models, but they have recently been connected in models for very high-dimensional data through a phenomenon of support vector proliferation, where every training example used to fit an SVM becomes a support vector. In this paper, we explore the generality of this phenomenon and make the following contributions. First, we prove a super-linear lower bound on the dimension (in terms of sample size) required for support vector proliferation in independent feature models, matching the upper bounds from previous works. We further identify a sharp phase transition in Gaussian feature models, bound the width of this transition, and give experimental support for its universality. Finally, we hypothesize that this phase transition occurs only in much higher-dimensional settings in the $\ell_1$ variant of the SVM, and we present a new geometric characterization of the problem that may elucidate this phenomenon for the general $\ell_p$ case.

cs.LG↗
arXiv2021

Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem

Given a target function $f$, how large must a neural network be in order to approximate $f$? Recent works examine this basic question on neural network \textit{expressivity} from the lens of dynamical systems and provide novel ``depth-vs-width'' tradeoffs for a large family of functions $f$. They suggest that such tradeoffs are governed by the existence of \textit{periodic} points or \emph{cycles} in $f$. Our work, by further deploying dynamical systems concepts, illuminates a more subtle connection between periodicity and expressivity: we prove that periodic points alone lead to suboptimal depth-width tradeoffs and we improve upon them by demonstrating that certain ``chaotic itineraries'' give stronger exponential tradeoffs, even in regimes where previous analyses only imply polynomial gaps. Contrary to prior works, our bounds are nearly-optimal, tighten as the period increases, and handle strong notions of inapproximability (e.g., constant $L_1$ error). More broadly, we identify a phase transition to the \textit{chaotic regime} that exactly coincides with an abrupt shift in other notions of function complexity, including VC-dimension and topological entropy.

cs.LG↗