Hemant Tyagi

Learn More
Automatic identification of bird calls without manual intervention has been a challenging task for meaningful research on the taxonomy and monitoring of bird migrations in ornithology. In this paper we apply several techniques used in speech recognition to the automatic identification of bird calls. A new technique which computes the ensemble average on the(More)
Numerous dimensionality reduction problems in data analysis involve the recovery of low-dimensional models or the learning of manifolds underlying sets of data. Many manifold learning methods require the estimation of the tangent space of the manifold at a point from locally available data samples. Local sampling conditions such as (i) the size of the(More)
We consider the problem of learning multi-ridge functions of the form f (x) = g(Ax) from point evaluations of f. We assume that the function f is defined on an 2-ball in R d , g is twice continuously differentiable almost everywhere, and A ∈ R k×d is a rank k matrix, where k d. We propose a randomized, polynomial-complexity sampling scheme for estimating(More)
We consider the stochastic and adversarial settings of continuum armed bandits where the arms are indexed by [0, 1] d. The reward functions r : [0, 1] d → R are assumed to intrinsically depend on at most k to be fixed across time, we propose a simple modification of the CAB1 algorithm where we construct the discrete set of sampling points to obtain a bound(More)
We study the problem of learning ridge functions of the form f (x) = g(a T x), x ∈ R d , from random samples. Assuming g to be a twice continuously differentiable function, we leverage techniques from low rank matrix recovery literature to derive a uniform approximation guarantee for estimation of the ridge function f. Our new analysis removes the de facto(More)
We consider the problem of learning sparse additive models, i.e., functions of the form: f (x) = l∈S φ l (x l), x ∈ R d from point queries of f. Here S is an unknown subset of coordinate variables with |S| = k d. Assuming φ l 's to be smooth, we propose a set of points at which to sample f and an efficient random-ized algorithm that recovers a uniform(More)
A function f : R d → R is referred to as a Sparse Additive Model (SPAM), if it is of the form f (x) = l∈S φ l (x l), where S ⊂ [d], |S| d. Assuming φ l 's and S to be unknown, the problem of estimating f from its samples has been studied extensively. In this work, we consider a generalized SPAM, allowing for second order interaction terms. For some S 1 ⊂(More)
We consider the problem of continuum armed bandits where the arms are indexed by a compact subset of ℝ d $\mathbb {R}^{d}$ . For large d, it is well known that mere smoothness assumptions on the reward functions lead to regret bounds that suffer from the curse of dimensionality. A typical way to tackle this in the literature has been to make further(More)
In this work we do a theoretical analysis of the local sampling conditions for points lying on a quadratic embedding of a Riemannian manifold in a Eu-clidean space. The embedding is assumed to be quadratic at a reference point P. Our analysis is based on the following criteria: (i) Local reconstruction error (ii) Local tangent space estimation accuracy. In(More)