Alt 09 Slides
Alt 09 Slides
yes, but
Direct product:
Monoidland Circuitland
all monoids NC 1
any nonsolvable group NC 1
Abelian groups boolean combinations of MOD gates
solvable groups poly-size, constant-depth circuits
made of MOD gates
aperiodic monoids poly-size constant-depth circuits
made of AND, OR, NOT gates
Group Description
Groupland Circuitland
Abelian groups MOD m ,
degree 1 polynomials over Zm
Gp or p-groups MOD pk ◦ NC 0 , MOD p ◦ NC 0 ,
constant degree polynomials over Fp
Nilpotent groups MOD m ◦ NC 0 ,
constant degree polynomials over Zm
Solvable groups constant-depth, poly-size modular circuits
Dramatis personae, aperiodic
In circuitland [GT03]:
[
B(DA) = rank-k decision trees
k
B(DA) ◦ NC 0 =
[
k -decision lists
k
Fact [GT06]
Learning programs over M requires 2n Membership queries if
M is not a group
or M is a nonsolvable group
Nilpotent groups
Equivalent to polynomials of constant degree over some Zm
Includes Abelian groups and Gp
Gp ? Abelian
Equivalent to depth-2, MOD p -of-MOD m circuits
Group lower bounds
Learning strategy:
1 Ask Membership queries with all assignments of weight cG
(or weight cG log s)
2 Build unique program consistent with the answers
Part 2 is a purely computational problem
Abelian groups
Theorem
If G is Abelian, then B(G) is learnable from Membership
queries in nO(1) time
Theorem
If G ∈ Gp ? Abelian, then B(G) is learnable from Membership
queries in nO(log s) time
Combine:
Tricks to make MOD p gates 0/1-valued [Fermat,BT94]
Subspace learning algorithm [HSW87]
Decision list / nested difference algorithm [R87,HSW87]
Composition theorem
DL ◦ MOD p ◦ NC 0
DL ◦ MOD p ◦ NC 0 subsumes:
DL ◦ MOD p : nested differences of linear subspaces of Fp
DL ◦ NC 0 : k -DL, so rank-k DT’s, k -CNF and k -DNF
MOD p ◦ NC 0 : constant-degree polynomials over Fp
strict width-2 branching programs [BBTV97]
Theorem
1. DL ◦ MOD p ◦ NC 0 = B(DA ? Gp )
0
m DL ◦ MOD m ◦ NC
S
2. = B(DA ? Nilpotent)
Theorem [BBBKV00]
Functions Σ∗ → Fp computed by Multiplicity Automata over Fp
are polynomial-time learnable from Membership and
Equivalence queries.
LGp
m Com [Weil 87]
The value of m1 . . . ms can be determined by counting mod p
the number of factorizations of the form a0 La1 La2 . . . ak −1 Lak ,
for L a commutative language (bool comb of)
Theorem
1. B(LGp
m Com) is polynomially simulated by MA over Fp
Conjecture
LGp
m Com is the largest class of monoids that is polynomially
simulated by MA