The partially observable generalized linear model (POGLM) is a powerful tool for understanding neural connectivity under the assumption of existing hidden neurons. With spike trains only recorded from visible neurons, existing works use variational inference to learn POGLM meanwhile presenting the difficulty of learning this latent variable model. There are two main issues: (1) the sampled Poisson hidden spike count hinders the use of the pathwise gradient estimator in VI; and (2) the existing design of the variational model is neither expressive nor time-efficient, which further affects the performance. For (1), we propose a new differentiable POGLM, which enables the pathwise gradient estimator, better than the score function gradient estimator used in existing works. For (2), we propose the forward-backward message-passing sampling scheme for the variational model. Comprehensive experiments show that our differentiable POGLMs with our forward-backward message passing produce a better performance on one synthetic and two real-world datasets. Furthermore, our new method yields more interpretable parameters, underscoring its significance in neuroscience.
Seoul National University（首尔国立大学）；Hanyang University（汉阳大学）
Recently, several studies proposed methods to utilize some classes of optimization problems in designing deep neural networks to encode constraints that conventional layers cannot capture. However, these methods are still in their infancy and require special treatments, such as analyzing the KKT condition, for deriving the backpropagation formula. In this paper, we propose a new layer formulation called the fixed-point iteration (FPI) layer that facilitates the use of more complicated operations in deep networks. The backward FPI layer is also proposed for backpropagation, which is motivated b…
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
Khoury College of Computer Sciences, Northeastern University（东北大学Khoury计算机科学学院）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Shanghai Qi Zhi Institute（上海期智研究院）
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
In this paper, we propose an algebraic formalization of the two important classes of dynamic programming algorithms called forward and forward-backward algorithms. They are generalized extensively in this study so that a wide range of other existing algorithms is subsumed. Forward algorithms generalized in this study subsume the ordinary forward algorithm on trellises for sequence labeling, the inside algorithm on derivation forests for CYK parsing, a unidirectional message passing on acyclic factor graphs, the forward mode of automatic differentiation on computation graphs with addition and m…
This work presents TorchRadon -- an open source CUDA library which contains a set of differentiable routines for solving computed tomography (CT) reconstruction problems. The library is designed to help researchers working on CT problems to combine deep learning and model-based approaches. The package is developed as a PyTorch extension and can be seamlessly integrated into existing deep learning training code. Compared to the existing Astra Toolbox, TorchRadon is up to 125 faster. The operators implemented by TorchRadon allow the computation of gradients using PyTorch backward(), and can ther…
Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation
Stanford University（斯坦福大学）；University of California, Los Angeles（加州大学洛杉矶分校）；LightSpeed Studios, Tencent America（腾讯美国光速工作室）；The University of Utah（犹他大学）
Automated Heterogeneous Network learning with Non-Recursive Message Passing
Chinese University of Hong Kong（香港中文大学）；Hong Kong Polytechnic University（香港理工大学）；The Hong Kong Polytechnic University（香港理工大学）；Chongqing University of Science and Technology（重庆科技学院）
Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
ETH Zurich, Zurich, Switzerland（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems, Tubingen, Germany（智能系统马克斯·普朗克研究所）；University of Tubingen, Tubingen, Germany（图宾根大学）
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given cost, over the space of doubly stochastic matrices. When the entropy regularization is added to the problem, the transportation plan can be efficiently computed with the Sinkhorn algorithm. Thanks to this breakthrough, optimal transport has been progressively extended to machine learning and statistical inference by introducing additional application-specific terms in the problem formulation. It is however challengi…
Massachusetts Institute of Technology（麻省理工学院）；Tsinghua University（清华大学）
Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and therefore they are significantly more computationally expe…
Improving Discrete Optimisation Via Decoupled Straight-Through Estimator
College of Design and Engineering, National University of Singapore, Singapore（设计与工程学院，新加坡国立大学）；Google Deepmind, California, USA（DeepMind，美国加州）；New York University, USA（纽约大学）
Technical University of Denmark（丹麦技术大学）；NKT Photonics（NKT光子学公司）；Politecnico di Torino（都灵理工大学）
The problem of Raman amplifier optimization is studied. A differentiable interpolation function is obtained for the Raman gain coefficient using machine learning (ML), which allows for the gradient descent optimization of forward-propagating Raman pumps. Both the frequency and power of an arbitrary number of pumps in a forward pumping configuration are then optimized for an arbitrary data channel load and span length. The forward propagation model is combined with an experimentally-trained ML model of a backward-pumping Raman amplifier to jointly optimize the frequency and power of the forward…
Understanding efficiency in high dimensional linear models is a longstanding problem of interest. Classical work with smaller dimensional problems dating back to Huber and Bickel has illustrated the benefits of efficient loss functions. When the number of parameters $p$ is of the same order as the sample size $n$, $p \approx n$, an efficiency pattern different from the one of Huber was recently established. In this work, we consider the effects of model selection on the estimation efficiency of penalized methods. In particular, we explore whether sparsity, results in new efficiency patterns wh…
