Collaborating Authors

Decoupling "when to update" from "how to update"

Neural Information Processing Systems

A useful approach to obtain data is to be creative and mine data from various sources, that were created for different purposes. Unfortunately, this approach often leads to noisy labels. In this paper, we propose a meta algorithm for tackling the noisy labels problem. The key idea is to decouple when to update'' from how to update''. We demonstrate the effectiveness of our algorithm by mining data for gender classification by combining the Labeled Faces in the Wild (LFW) face recognition dataset with a textual genderizing service, which leads to a noisy dataset.

Graph Matching via Multiplicative Update Algorithm

Neural Information Processing Systems

As a fundamental problem in computer vision, graph matching problem can usually be formulated as a Quadratic Programming (QP) problem with doubly stochastic and discrete (integer) constraints. Since it is NP-hard, approximate algorithms are required. In this paper, we present a new algorithm, called Multiplicative Update Graph Matching (MPGM), that develops a multiplicative update technique to solve the QP matching problem. MPGM has three main benefits: (1) theoretically, MPGM solves the general QP problem with doubly stochastic constraint naturally whose convergence and KKT optimality are guaranteed. Experimental results show the benefits of MPGM algorithm.

Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update Machine Learning

We propose Episodic Backward Update - a new algorithm to boost the performance of a deep reinforcement learning agent by a fast reward propagation. In contrast to the conventional use of the experience replay with uniform random sampling, our agent samples a whole episode and successively propagates the value of a state to its previous states. Our computationally efficient recursive algorithm allows sparse and delayed rewards to propagate efficiently through all transitions of a sampled episode. We evaluate our algorithm on 2D MNIST Maze environment and 49 games of the Atari 2600 environment and show that our method improves sample efficiency with a competitive amount of computational cost.

Training Algorithms for Hidden Markov Models using Entropy Based Distance Functions

Neural Information Processing Systems

By adapting a framework used for supervised learning, we construct iterative algorithms that maximize the likelihood of the observations while also attempting to stay "close" to the current estimated parameters. We use a bound on the relative entropy between the two HMMs as a distance measure betweenthem. The result is new iterative training algorithms which are similar to the EM (Baum-Welch) algorithm for training HMMs. The proposed algorithms are composed of a step similar to the expectation step of Baum-Welch and a new update of the parameters which replaces the maximization (re-estimation) step. The algorithm takes only negligibly moretime per iteration and an approximated version uses the same expectation step as Baum-Welch.

Gradient Descent Optimization Techniques.


Gradient descent is one of the most popular algorithms to perform optimization and by far the most common way to optimize neural networks. At the same time, every state-of-the-art Deep Learning library contains implementations of various algorithms to optimize gradient descent . This blog post aims at providing you with intuitions towards the behaviour of different algorithms for optimizing gradient descent that will help you put them to use. Gradient descent is a way to minimize an objective function J(θ) parameterized by a model's parameters by updating the parameters in the opposite direction of the gradient of the objective function .J(θ) w.r.t. to the parameters. The learning rate η determines the size of the steps we take to reach a (local) minimum.