English
Related papers

Related papers: Direct Optimization through $\arg \max$ for Discre…

200 papers

Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. The reparameterization…

Machine Learning · Statistics 2020-02-13 Christian A. Naesseth , Francisco J. R. Ruiz , Scott W. Linderman , David M. Blei

Learning models with categorical variables requires optimizing expectations over discrete distributions, a setting in which stochastic gradient-based optimization is challenging due to the non-differentiability of categorical sampling. A…

Machine Learning · Computer Science 2026-02-10 Samson Gourevitch , Alain Durmus , Eric Moulines , Jimmy Olsson , Yazid Janati

Variational optimization of orbitals in time-independent density functional calculations of excited electronic states presents a significant challenge, as excited states typically correspond to saddle points on the electronic energy…

Chemical Physics · Physics 2026-04-02 Yorick L. A. Schmerwitz , Elli Selenius , Gianluca Levi

The Gumbel trick is a method to sample from a discrete probability distribution, or to estimate its normalizing partition function. The method relies on repeatedly applying a random perturbation to the distribution in a particular way, each…

Machine Learning · Statistics 2017-06-14 Matej Balog , Nilesh Tripuraneni , Zoubin Ghahramani , Adrian Weller

The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning…

Machine Learning · Computer Science 2023-11-23 Zhang Zhang , Ruyi Tao , Jiang Zhang

The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Although there is…

Machine Learning · Statistics 2018-12-31 Ming Xu , Matias Quiroz , Robert Kohn , Scott A. Sisson

Discrete and especially binary random variables occur in many machine learning models, notably in variational autoencoders with binary latent states and in stochastic binary networks. When learning such models, a key tool is an estimator of…

Machine Learning · Computer Science 2021-10-18 Alexander Shekhovtsov

Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word…

Computation and Language · Computer Science 2017-11-20 Raphael Shu , Hideki Nakayama

Learning to control the structure of sentences is a challenging problem in text generation. Existing work either relies on simple deterministic approaches or RL-based hard structures. We explore the use of structured variational…

Computation and Language · Computer Science 2020-12-01 Yao Fu , Chuanqi Tan , Bin Bi , Mosha Chen , Yansong Feng , Alexander M. Rush

The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random…

Machine Learning · Computer Science 2017-03-07 Chris J. Maddison , Andriy Mnih , Yee Whye Teh

In the context of regularized loss minimization with polyhedral gauges, we show that for a broad class of loss functions (possibly non-smooth and non-convex) and under a simple geometric condition on the input data it is possible to…

Machine Learning · Statistics 2020-12-01 Amin Jalali

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for…

Computation and Language · Computer Science 2021-09-16 Giangiacomo Mercatali , André Freitas

Recent studies have demonstrated the strong empirical performance of diffusion models on discrete sequences across domains from natural language to biological sequence generation. For example, in the protein inverse folding task,…

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

Machine Learning · Computer Science 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

Machine Learning · Computer Science 2020-10-26 Guy Lorberbom , Chris J. Maddison , Nicolas Heess , Tamir Hazan , Daniel Tarlow

Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are compositional, tend to generalize better, and are more…

Machine Learning · Computer Science 2023-07-27 David Friede , Mathias Niepert

We study the implicit regularization of gradient descent towards structured sparsity via a novel neural reparameterization, which we call a diagonally grouped linear neural network. We show the following intriguing property of our…

Machine Learning · Statistics 2023-01-31 Jiangyuan Li , Thanh V. Nguyen , Chinmay Hegde , Raymond K. W. Wong

The use of directly modulated lasers (DMLs) is attractive in low-power, cost-constrained short-reach optical links. However, their limited modulation bandwidth can induce waveform distortion, undermining their data throughput. Traditional…

Signal Processing · Electrical Eng. & Systems 2024-06-21 Sergio Hernandez F. , Christophe Peucheret , Francesco Da Ros , Darko Zibar

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation…

Optimization and Control · Mathematics 2019-10-15 Sheheryar Mehmood , Peter Ochs

Important applications such as mobile computing require reducing the computational costs of neural network inference. Ideally, applications would specify their preferred tradeoff between accuracy and speed, and the network would optimize…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Charles Herrmann , Richard Strong Bowen , Ramin Zabih