109 citations · 194 across the 11 of their papers we have counts for
12 papers
AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles
Charles Weill, Javier Gonzalvo, Vitaly Kuznetsov +9
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspire…
Foundations of Sequence-to-Sequence Modeling for Time Series
Vitaly Kuznetsov, Zelda Mariet
The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interes…
Online Non-Additive Path Learning under Full and Partial Information
Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri +2
We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction. We pre…
Theory and Algorithms for Forecasting Time Series
Vitaly Kuznetsov, Mehryar Mohri
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-depen…
Discrepancy-Based Algorithms for Non-Stationary Rested Bandits
Corinna Cortes, Giulia DeSalvo, Vitaly Kuznetsov +2
We study the multi-armed bandit problem where the rewards are realizations of general non-stationary stochastic processes, a setting that generalizes many existing lines of work an…
AdaNet: Adaptive Structural Learning of Artificial Neural Networks
Corinna Cortes, Xavi Gonzalvo, Vitaly Kuznetsov +2
We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are b…
Structured Prediction Theory Based on Factor Graph Complexity
Corinna Cortes, Mehryar Mohri, Vitaly Kuznetsov +1
We present a general theoretical analysis of structured prediction with a series of new results. We give new data-dependent margin guarantees for structured prediction for a very w…
Voted Kernel Regularization
Corinna Cortes, Prasoon Goyal, Vitaly Kuznetsov +1
This paper presents an algorithm, Voted Kernel Regularization , that provides the flexibility of using potentially very complex kernel functions such as predictors based on much hi…
Nested Recursions, Simultaneous Parameters and Tree Superpositions
Abraham Isgur, Vitaly Kuznetsov, Mustazee Rahman +1
We apply a tree-based methodology to solve new, very broadly defined families of nested recursions of the general form R(n)=sum_{i=1}^k R(n-a_i-sum_{j=1}^p R(n-b_{ij})), where a_i…
Nested recursions with ceiling function solutions
Abraham Isgur, Vitaly Kuznetsov, Stephen M. Tanny
Consider a nested, non-homogeneous recursion R(n) defined by R(n) = \sum_{i=1}^k R(n-s_i-\sum_{j=1}^{p_i} R(n-a_ij)) + nu, with c initial conditions R(1) = xi_1 > 0,R(2)=xi_2 > 0,…
A combinatorial approach for solving certain nested recursions with non-slow solutions
Abraham Isgur, Vitaly Kuznetsov, Stephen Tanny
We define the generalized Golomb triangular recursion by g_{j,s,lambda}(n) = g_{j,s,lambda}(n - s - g_{j,s,lambda}(n-j)) + λj. For particular choices of the initial conditions, we…
Sums of Ceiling Functions Solve Nested Recursions
Rafal Drabek, Abraham Isgur, Vitaly Kuznetsov +1
It is known that, for given integers s \geq 0 and j > 0, the nested recursion R(n) = R(n - s - R(n - j)) + R(n - 2j - s - R(n - 3j)) has a closed form solution for which a combinat…