The following pages link to Rocco A. Servedio (Q371199):
Displaying 50 items.
- Improved approximation of linear threshold functions (Q371200) (← links)
- Learning intersections and thresholds of halfspaces (Q598257) (← links)
- Learning random monotone DNF (Q628302) (← links)
- Efficiently testing sparse \(\text{GF}(2)\) polynomials (Q644810) (← links)
- On learning embedded midbit functions (Q817826) (← links)
- Learning unions of \(\omega(1)\)-dimensional rectangles (Q950197) (← links)
- DNF are teachable in the average case (Q1009216) (← links)
- Computing sparse permanents faster (Q1044712) (← links)
- Boosting and hard-core set construction (Q1394786) (← links)
- (Q1603391) (redirect page) (← links)
- On the limits of efficient teachability (Q1603392) (← links)
- A new central limit theorem and decomposition for Gaussian polynomials, with an application to deterministic approximate counting (Q1656545) (← links)
- Optimal mean-based algorithms for trace reconstruction (Q1737958) (← links)
- Monotone Boolean formulas can approximate monotone linear threshold functions (Q1878411) (← links)
- On learning monotone DNF under product distributions (Q1881232) (← links)
- Learning functions of \(k\) relevant variables (Q1886314) (← links)
- Learning DNF in time \(2^{\widetilde O(n^{1/3})}\) (Q1887713) (← links)
- Random classification noise defeats all convex potential boosters (Q1959553) (← links)
- Quantitative correlation inequalities via extremal power series (Q2140009) (← links)
- Learning Poisson binomial distributions (Q2345953) (← links)
- Exponentially improved algorithms and lower bounds for testing signed majorities (Q2354020) (← links)
- Discriminative learning can succeed where generative learning fails (Q2379956) (← links)
- On PAC learning algorithms for rich Boolean function classes (Q2382283) (← links)
- The inverse Shapley value problem (Q2411521) (← links)
- Learning intersections of halfspaces with a margin (Q2462501) (← links)
- Quantum algorithms for learning and testing juntas (Q2462663) (← links)
- Every linear threshold function has a low-weight approximator (Q2472433) (← links)
- Extremal properties of polynomial threshold functions (Q2475403) (← links)
- Improved bounds on quantum learning algorithms (Q2491374) (← links)
- Polynomial certificates for propositional classes (Q2495655) (← links)
- Learning DNF from random walks (Q2568457) (← links)
- Smooth Boolean Functions are Easy (Q2800553) (← links)
- A Robust Khintchine Inequality, and Algorithms for Computing Optimal Constants in Fourier Analysis and High-Dimensional Geometry (Q2808162) (← links)
- Bounding the average sensitivity and noise sensitivity of polynomial threshold functions (Q2875180) (← links)
- (Q2880992) (← links)
- (Q2933930) (← links)
- On the Weight of Halfspaces over Hamming Balls (Q2935257) (← links)
- Boolean Function Monotonicity Testing Requires (Almost) n 1/2 Non-adaptive Queries (Q2941544) (← links)
- Low-weight halfspaces for sparse boolean vectors (Q2986855) (← links)
- The Chow Parameters Problem (Q2999860) (← links)
- (Q3002770) (← links)
- (Q3002810) (← links)
- (Q3002813) (← links)
- Testing Halfspaces (Q3053158) (← links)
- A Canonical Form for Testing Boolean Function Properties (Q3088118) (← links)
- (Q3093302) (← links)
- (Q3093360) (← links)
- (Q3148821) (← links)
- (Q3148827) (← links)
- Perceptron, Winnow, and PAC Learning (Q3149871) (← links)
