14
Stack Exchange
votes

The best known upper bound for two-way probabilistic finite automata with one-counter

Posted on 4/13/2012
UQ ID:48
Science
Theoretical Computer Science
Original

It is known that the class of languages recognized by two-way deterministic finite automata with one-counter (2D1CAs) is a proper subset of (deterministic log-space): A 2D1CA can run at most steps if it halts on a given input, and there is a language in , i.e. \begin{equation} \mathtt{DG} = \lbrace w_0 $ w_1 $ \cdots $ w_k \mid k \geq 1, w_{i \in \lbrace 0, \ldots, k \rbrace} \in \lbrace a,b\rbrace^* , \mbox{ and } w_0=w_i \mbox{ for some } 1 \leq i \leq k \rbrace, \end{equation} which cannot be recognized by any 2D1CA (Duris and Galil, 1982).

What happens if such an automaton can use a coin?

More precisely, what is the best known upper bound for the class of languages recognized by two-way probabilistic finite automata with one-counter (2P1CAs) with bounded error?

Keywords & Tags
cc.complexity-theory
reference-request
automata-theory
upper-bounds
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The class of languages recognized by two-way probabilistic finite automata with one-counter (2P1CAs) with bounded error is known to be contained within the complexity class BPL (bounded-error probabilistic log-space).

BPL consists of languages decidable by probabilistic Turing machines using O(log n) space with bounded error probability (less than 1/2). Two-way probabilistic finite automata ...

0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Short answer: They are contained in BPL, and hence in DSPACE(log^{3/2} n) and in Σ2^L ∩ Π2^L (in particular, in P). No substantially tighter, model-specific upper bound is known.

Reasoning:

  • If a two-way 1-counter automaton halts on a given input, then every computation path halts in O(n^2) steps (the Duris–Galil bound). A probabilistic machine’s computation paths are just deterministic runs wi...
0 model reviews
0 human reviews
No reviews yet

o3 Pro

UQ Validated
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Let M be a two–way probabilistic one–counter automaton (2P1CA) that works with bounded error, say it accepts every word w that is in the language with probability ≥ 2/3 and rejects every other word with probability ≥ 2/3.
Fix an input word w of length n.
During the run of M on w a configuration consists of

• the finite control state of M (|Q| possibilities)
• the current head position i (0 ...

0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Upper Bounds for Two-Way Probabilistic Finite Automata with One-Counter (2P1CAs)

The question is asking about the best known upper bound for languages recognized by two-way probabilistic finite automata with one counter (2P1CAs) with bounded error.

From what I understand of the research literature, the best known upper bound for 2P1CAs with bounded error is likely BPL (Bounded-error Probab...

0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

Failed UQ Validation
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

Excellent question. It touches on a classic but non-trivial result in automata theory and computational complexity.

Summary

The best known upper bound for the class of languages recognized by two-way probabilistic finite automata with one-counter (2P1CA) with bounded error is P (polynomial time).

This result is due to Ioan I. Macarie and Mitsunori Ogihara in their 1998 paper:

Macar...

0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

The question asks about the computational power of two-way probabilistic finite automata with one counter (2P1CAs) with bounded error, specifically what upper bounds are known for this model.

To answer this comprehensively:

Known Upper Bounds

The best known upper bound for 2P1CAs with bounded error is BPL (bounded-error probabilistic logspace). This can be shown through the following rea...

0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Below is what is known about the upper‐bound of the 2‐way probabilistic one–counter machines (2P1CAs) with bounded error. In all cases the proofs are just “cook‐ups’’ of a finite (but large) absorbing Markov chain over the set of configurations, and then solving for the absorption probabilities.

  1. Configuration‐graph size.
    – A single configuration is determined by
    • the contro...
0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> We are given a question about the best known upper bound for two-way probabilistic finite automata with one-counter (2P1CAs) with bounded error.

First, recall that a two-way probabilistic finite automaton with one-counter (2P1CA) is a two-way automaton that has a finite state control, a read-only input tape with endmarkers, and a counter that can store an integer and be incremented, decr...

0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Let

2P1CA = the class of languages that can be recognised with two–sided bounded error
( say ≤ 1/3 ) by two–way probabilistic finite automata equipped with one counter and that halt with probability 1 on every input.

The best upper bound that is currently known for 2P1CA is the bounded-error probabilistic log–space class BPL (and therefore also P).

Why 2P1CA ⊆ ...

0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer