Title: Polynomial Time Probabilistic Learning of a Subclass of Linear Languages with Queries
1Polynomial Time Probabilistic Learning of a
Subclass of Linear Languageswith Queries
- Yasuhiro TAJIMA, Yoshiyuki KOTANI
- Tokyo Univ. of Agri. Tech.
2This talk
- Probabilistic learning algorithm of a subclass of
linear languages with membership queries - learning via queries special examples ?
Probabilistic learning - Use translation algorithms
- representative sample ? random examples
- equivalence query ? random examples
3Motivations
- A simple deterministic grammar (SDG) has
- at most one rule for every
pair of - ? learning algorithm for SDG from
- membership queries
- representative sample
- ? for linear languages
(Tajima et al. 2004)
CFLs
Linear
SDLs
Regular
4Linear grammar
A context-free grammar is a linear grammar if
every rule is of the form
Any linear grammar can be written in RL-linear
s.t. if every rule is of the form
and
5Strict-deterministic linear grammar
An RL-linear is a Strict-det linear if, for any
pair of rules
or
for some a,B,c,D
has only left linear rules ( or right linear
rules)
Ex)
6Deterministic linear grammar
- A linear grammar is deterministic linear (DL)
- if every rule is of the form
or
and
Theorem(de la Higuera, Oncina 2002) DL
identifiable in the limit from polynomial time
and data
7MAT learning (Angluin1987)
learner hypothesis
teacher target language
membership query
yes or no
hypothesis
equivalence query
counter example
8PAC learning (Valiant 1984)
- PAC Probabilistic Approximate Correct
probability distribution
learning algorithm
hypothesis
target concept
example
is PAC
9Equivalence query ? PAC learning algorithm
(Angluin1987)
If a hypothesis is consistent with
examples
If there is a consistent hypothesis ? PAC
learnable
consistent with examples
10Probabilistic learning with queries
Example oracle
Learning algorithm
hypothesis
Membership query
Yes or No
target language
11Representative sample for a Strict-det
representative sample (RS)
for some
All rules are used to generate Q
12Example
then
is a representative sample (RS)
13Rule occurring probability
a target grammar a probability
distribution on for an
example error parameter
confidential parameter the size of
target grammars rules For every rule
, define
14 is a rule occurring probability s.t. appears
in the derivation of an example
- is an probability that
-
- and
- is used in the derivation
15Let Suppose The set of m-examples contains a
set of RS with the probability Proof Any
rule doesnt appear in derivations of
m-examples occurs
RS
16We can conclude that
- Equivalence query can be replaced by
- random examples
- Representative sample can be replaced by
- random examples
17membership oracle
example oracle
probabilistic learning algorithm with queries
n-random examples
m-random examples
consistency check
query
response
nega
equivalence query
posi
learning algorithm
membership query
representative sample
18Learning algorithm via queries and RS
-
- while (finish 0) begin
- make nonterminals from
- make rules and hypothesis
- if (equivalence query for responds yes)
- output , finish 1
- else
- update by the counterexample
- end
19Making nonterminals
then
a nonterminal an equivalence class contains
(u,v,w)
20Making rules
Make all rules as follows except for not
consistent with query results
Select a hypothesis randomly
21Exact learning of strict-det
- Strict-det is polynomial time exact learnable via
- membership queries, and
- a representative samples (RS)
- c.f. Angluin(1980) for regular sets
The learning algorithm overview
a set of Strict-det (not bounded by a
polynomial)
Chose one randomly, Equivalence query
SD
SD
SD
RS
Possible rules
SD
SD
SD
SD
The correct hypothesis
Witnesses delete incorrect rule
22Conclusions
- Strict-det linear language can be probabilistic
learnable with queries in polynomial time - Future works
- Identification from polynomial time and data
(teachability) - RS ? Correction queries
23(No Transcript)
24Theorem
- Strict-det linear languages are
- polynomial time probabilistic learnable with
membership queries
25Simple Deterministic Languages
- Context-free grammar(CFG)
- in 2-standard Greibach normal form is
- Simple Deterministic Grammar (SDG) iff
- is unique for every and
- Simple Deterministic Language (SDL) is the
generated language by a SDG
26Representative sample for an SDG
representative sample (RS)
for some
All rules are used to generate Q
27Example
then
is a representative sample (RS)
28PAC learning
(Valiant1984)
Target language
Hypothesis language
on
Probability distribution
A PAC learning algorithm outputs such that
where
29Query learning of SDLs
(Tajima2000)
- SDLs are polynomial time learnable via membership
queries and a representative sample
the teacher
the learner
membership query
yes / no
representative sample
at the beginning
representative sample a special finite subset
of
30Learning model
the learner
the teacher
membership query
yes / no
representative sample
at the beginning
representative sample a special finite subset
of