paper-with-me

홈 › Papers

Ehrenfeucht-Haussler Rank and Chain of Thought

2025-01-22 · Pablo Barceló, Alexander Kozachinskiy, Tomasz Steifer

The notion of rank of a Boolean function has been a cornerstone in the theory of PAC learning, enabling quasipolynomial-time learning algorithms for polynomial-size decision trees. We present a novel characterization of rank, grounded in the well-known Transformer architecture. We show that the rank of a function $f$ corresponds to the minimum number of Chain of Thought (CoT) steps required by a single-layer transformer decoder with hard attention to compute $f$. Based on this characterization we establish tight bounds on the number of CoT steps required for specific problems, showing that $\ell$-fold function composition necessitates exactly $\ell$ CoT steps. Furthermore, we analyze the problem of identifying the position of the $k$-th occurrence of 1 in a Boolean sequence, proving that it requires $k$ CoT steps.

📄 PDF Abstract BibTeX arXiv:2501.12997

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderHard AttentionPAC learningPosition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Fast decision tree learning solves hard coding-theoretic problems

2024-09-19 · Caleb Koch, Carmen Strassle, Li-Yang Tan

We connect the problem of properly PAC learning decision trees to the parameterized Nearest Codeword Problem ($k$-NCP). Despite significant effort by the respective communities, algorithmic progress on both problems has …

PAC learning

Optimal Bounds on the VC-dimension

2018-07-20 · Monika Csikos, Andrey Kupavskii, Nabil H. Mustafa

The VC-dimension of a set system is a way to capture its complexity and has been a key parameter studied extensively in machine learning and geometry communities. In this paper, we resolve two longstanding open problems …

BIG-bench Machine LearningOpen-Ended Question Answering

Open Problem: Properly learning decision trees in polynomial time?

2022-06-29 · Guy Blanc, Jane Lange, Mingda Qiao, Li-Yang Tan

The authors recently gave an $n^{O(\log\log n)}$ time membership query algorithm for properly learning decision trees under the uniform distribution (Blanc et al., 2021). The previous fastest algorithm for this problem r…

Top-down induction of decision trees: rigorous guarantees and inherent limitations

2019-11-18 · Guy Blanc, Jane Lange, Li-Yang Tan

Consider the following heuristic for building a decision tree for a function $f : \{0,1\}^n \to \{\pm 1\}$. Place the most influential variable $x_i$ of $f$ at the root, and recurse on the subfunctions $f_{x_i=0}$ and $f…

Properly learning decision trees in almost polynomial time

2021-09-01 · Guy Blanc, Jane Lange, Mingda Qiao, Li-Yang Tan

We give an $n^{O(\log\log n)}$-time membership query algorithm for properly and agnostically learning decision trees under the uniform distribution over $\{\pm 1\}^n$. Even in the realizable setting, the previous fastest…