Nearly optimal solutions for the Chow Parameters Problem and low-weight approximation of halfspaces
This provides efficient solutions for reconstructing LTFs from their Chow parameters, with applications in learning theory, though it is incremental over prior work.
The paper tackles the Chow Parameters Problem by developing a new algorithm that reconstructs a linear threshold function (LTF) from approximate Chow parameters in time $ ilde{O}(n^2)\cdot (1/\eps)^{O(\log^2(1/\eps))}$, significantly improving the previous exponential-time algorithm, and shows that any LTF can be approximated by one with integer weights bounded by $\sqrt{n} \cdot (1/\eps)^{O(\log^2(1/\eps))}$, close to known lower bounds.
The \emph{Chow parameters} of a Boolean function $f: \{-1,1\}^n \to \{-1,1\}$ are its $n+1$ degree-0 and degree-1 Fourier coefficients. It has been known since 1961 (Chow, Tannenbaum) that the (exact values of the) Chow parameters of any linear threshold function $f$ uniquely specify $f$ within the space of all Boolean functions, but until recently (O'Donnell and Servedio) nothing was known about efficient algorithms for \emph{reconstructing} $f$ (exactly or approximately) from exact or approximate values of its Chow parameters. We refer to this reconstruction problem as the \emph{Chow Parameters Problem.} Our main result is a new algorithm for the Chow Parameters Problem which, given (sufficiently accurate approximations to) the Chow parameters of any linear threshold function $f$, runs in time $\tilde{O}(n^2)\cdot (1/\eps)^{O(\log^2(1/\eps))}$ and with high probability outputs a representation of an LTF $f'$ that is $\eps$-close to $f$. The only previous algorithm (O'Donnell and Servedio) had running time $\poly(n) \cdot 2^{2^{\tilde{O}(1/\eps^2)}}.$ As a byproduct of our approach, we show that for any linear threshold function $f$ over $\{-1,1\}^n$, there is a linear threshold function $f'$ which is $\eps$-close to $f$ and has all weights that are integers at most $\sqrt{n} \cdot (1/\eps)^{O(\log^2(1/\eps))}$. This significantly improves the best previous result of Diakonikolas and Servedio which gave a $\poly(n) \cdot 2^{\tilde{O}(1/\eps^{2/3})}$ weight bound, and is close to the known lower bound of $\max\{\sqrt{n},$ $(1/\eps)^{Ω(\log \log (1/\eps))}\}$ (Goldberg, Servedio). Our techniques also yield improved algorithms for related problems in learning theory.