NoPE: The Counting Power of Transformers with No Positional Encodings

Positional Encodings (PEs) seem to be indispensable for ensuring expressiveness of transformers; without them attention transformers reduce to a bag-of-word model. NoPE-transformers (i.e. with No PEs) with unique hard attention mechanisms were very recently shown to only be able to express regular languages, i.e., with limited counting ability. This paper shows that, with average hard attention mechanisms, NoPE-transformers are still surprisingly expressive: they can express counting languages corresponding to nonnegative integer solutions to multivariate polynomial equations (i.e. Diophantine equations), reasoning about which is well-known to be undecidable. In fact, we provide a precise characterization of languages expressible by Average Hard Attention NoPE-Transformers (NoPE-AHATs): they correspond precisely to what we call \emph{semi-algebraic sets}, i.e., finite unions of sets of nonnegative integer solutions to systems of multivariate polynomial inequations. We obtain several interesting consequences of our characterization. Firstly, NoPE-transformers can express counting properties that are far more complex than established models like simplified counter machines and Petri nets, but cannot express a very simple counting property of PARITY. Secondly, the problem of analyzing NoPE-transformers is undecidable, e.g., whether a given NoPE transformer classifies all input strings in one class. To complement our results, we exhibit a counting language that is not expressible by average hard attention transformers even with arbitrary PEs but is expressible in the circuit complexity class TC$^0$, answering an open problem.

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models

Understanding how Transformers work and how they process information is key to the theoretical and empirical advancement of these machines. In this work, we demonstrate the existence of two phenomena in Transformers, namely isolation and continuity. Both of these phenomena hinder Transformers to learn even simple pattern sequences. Isolation expresses that any learnable sequence must be isolated from another learnable sequence, and hence some sequences cannot be learned by a single Transformer at the same time. Continuity entails that an attractor basin forms around a learned sequence, such that any sequence falling in that basin will collapse towards the learned sequence. Here, we mathematically prove these phenomena emerge in all Transformers that use compact positional encoding, and design rigorous experiments, demonstrating that the theoretical limitations we shed light on occur on the practical scale.

Strassen Attention: Unlocking Compositional Abilities in Transformers Based on a New Lower Bound Method

We propose a novel method to evaluate the theoretical limits of Transformers, allowing us to prove the first lower bounds against one-layer softmax Transformers with infinite precision. We establish those bounds for three tasks that require advanced reasoning. The first task, Match3 (Sanford et al., 2023), requires looking at all triples of positions. The second and third tasks address compositionality-based reasoning: one is composition of functions (Peng et al., 2024) and the other is composition of binary relations. We formally prove the inability of one-layer softmax Transformers to solve any of these tasks. In an attempt to overcome these limitations, we introduce Strassen attention and prove that with this mechanism a one-layer Transformer can in principle solve all these tasks. We also show that it enjoys sub-cubic running-time complexity, making it more scalable than similar previously proposed mechanisms, such as higher-order attention (Sanford et al., 2023). To complement our theoretical findings, we experimentally studied Strassen attention and compared it against standard (Vaswani et al, 2017), higher-order attention (Sanford et al., 2023) and triangular attention (Bergen et al. 2021). Our results help to disentangle all these attention mechanisms, highlighting their strengths and limitations. In particular, Strassen attention outperforms standard attention significantly on all the tasks. Altogether, understanding the theoretical limitations can guide research towards scalable attention mechanisms that improve the reasoning abilities of Transformers.

Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations

Despite the wide use of $k$-Nearest Neighbors as classification models, their explainability properties remain poorly understood from a theoretical perspective. While nearest neighbors classifiers offer interpretability from a "data perspective", in which the classification of an input vector $\bar{x}$ is explained by identifying the vectors $\bar{v}_1, \ldots, \bar{v}_k$ in the training set that determine the classification of $\bar{x}$, we argue that such explanations can be impractical in high-dimensional applications, where each vector has hundreds or thousands of features and it is not clear what their relative importance is. Hence, we focus on understanding nearest neighbor classifications through a "feature perspective", in which the goal is to identify how the values of the features in $\bar{x}$ affect its classification. Concretely, we study abductive explanations such as "minimum sufficient reasons", which correspond to sets of features in $\bar{x}$ that are enough to guarantee its classification, and "counterfactual explanations" based on the minimum distance feature changes one would have to perform in $\bar{x}$ to change its classification. We present a detailed landscape of positive and negative complexity results for counterfactual and abductive explanations, distinguishing between discrete and continuous feature spaces, and considering the impact of the choice of distance function involved. Finally, we show that despite some negative complexity results, Integer Quadratic Programming and SAT solving allow for computing explanations in practice.

A completely uniform transformer for parity

We construct a 3-layer constant-dimension transformer, recognizing the parity language, where neither parameter matrices nor the positional encoding depend on the input length. This improves upon a construction of Chiang and Cholak who use a positional encoding, depending on the input length (but their construction has 2 layers).

Lower bounds on transformers with infinite precision

In this note, we use the VC dimension technique to prove the first lower bound against one-layer softmax transformers with infinite precision. We do so for two tasks: function composition, considered by Peng, Narayanan, and Papadimitriou, and the SUM$_2$ task, considered by Sanford, Hsu, and Telgarsky.

Effective Littlestone Dimension

Delle Rose et al.~(COLT'23) introduced an effective version of the Vapnik-Chervonenkis dimension, and showed that it characterizes improper PAC learning with total computable learners. In this paper, we introduce and study a similar effectivization of the notion of Littlestone dimension. Finite effective Littlestone dimension is a necessary condition for computable online learning but is not a sufficient one -- which we already establish for classes of the effective Littlestone dimension 2. However, the effective Littlestone dimension equals the optimal mistake bound for computable learners in two special cases: a) for classes of Littlestone dimension 1 and b) when the learner receives as additional information an upper bound on the numbers to be guessed. Interestingly, finite effective Littlestone dimension also guarantees that the class consists only of computable functions.

On dimensionality of feature vectors in MPNNs

We revisit the classical result of Morris et al.~(AAAI'19) that message-passing graphs neural networks (MPNNs) are equal in their distinguishing power to the Weisfeiler--Leman (WL) isomorphism test. Morris et al.~show their simulation result with ReLU activation function and $O(n)$-dimensional feature vectors, where $n$ is the number of nodes of the graph. By introducing randomness into the architecture, Aamand et al.~(NeurIPS'22) were able to improve this bound to $O(\log n)$-dimensional feature vectors, again for ReLU activation, although at the expense of guaranteeing perfect simulation only with high probability. Recently, Amir et al.~(NeurIPS'23) have shown that for any non-polynomial analytic activation function, it is enough to use just 1-dimensional feature vectors. In this paper, we give a simple proof of the result of Amit et al.~and provide an independent experimental validation of it.

Logical Languages Accepted by Transformer Encoders with Hard Attention

We contribute to the study of formal languages that can be recognized by transformer encoders. We focus on two self-attention mechanisms: (1) UHAT (Unique Hard Attention Transformers) and (2) AHAT (Average Hard Attention Transformers). UHAT encoders are known to recognize only languages inside the circuit complexity class ${\sf AC}^0$, i.e., accepted by a family of poly-sized and depth-bounded boolean circuits with unbounded fan-ins. On the other hand, AHAT encoders can recognize languages outside ${\sf AC}^0$), but their expressive power still lies within the bigger circuit complexity class ${\sf TC}^0$, i.e., ${\sf AC}^0$-circuits extended by majority gates. We first show a negative result that there is an ${\sf AC}^0$-language that cannot be recognized by an UHAT encoder. On the positive side, we show that UHAT encoders can recognize a rich fragment of ${\sf AC}^0$-languages, namely, all languages definable in first-order logic with arbitrary unary numerical predicates. This logic, includes, for example, all regular languages from ${\sf AC}^0$. We then show that AHAT encoders can recognize all languages of our logic even when we enrich it with counting terms. We apply these results to derive new results on the expressive power of UHAT and AHAT up to permutation of letters (a.k.a. Parikh images).

Simple online learning with consistency oracle

We consider online learning in the model where a learning algorithm can access the class only via the consistency oracle -- an oracle, that, at any moment, can give a function from the class that agrees with all examples seen so far. This model was recently considered by Assos et al. (COLT'23). It is motivated by the fact that standard methods of online learning rely on computing the Littlestone dimension of subclasses, a problem that is computationally intractable. Assos et al. gave an online learning algorithm in this model that makes at most $C^d$ mistakes on classes of Littlestone dimension $d$, for some absolute unspecified constant $C > 0$. We give a novel algorithm that makes at most $O(256^d)$ mistakes. Our proof is significantly simpler and uses only very basic properties of the Littlestone dimension. We also observe that there exists no algorithm in this model that makes at most $2^{d+1}-2$ mistakes. We also observe that our algorithm (as well as the algorithm of Assos et al.) solves an open problem by Hasrati and Ben-David (ALT'23). Namely, it demonstrates that every class of finite Littlestone dimension with recursively enumerable representation admits a computable online learner (that may be undefined on unrealizable samples).