paper-with-me

홈 › Papers

Fixed-point optimization of deep neural networks with adaptive step size retraining

2017-02-27 · Sungho Shin, Yoonho Boo, Wonyong Sung

Fixed-point optimization of deep neural networks plays an important role in hardware based design and low-power implementations. Many deep neural networks show fairly good performance even with 2- or 3-bit precision when quantized weights are fine-tuned by retraining. We propose an improved fixedpoint optimization algorithm that estimates the quantization step size dynamically during the retraining. In addition, a gradual quantization scheme is also tested, which sequentially applies fixed-point optimizations from high- to low-precision. The experiments are conducted for feed-forward deep neural networks (FFDNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

📄 PDF Abstract BibTeX arXiv:1702.08171

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Gradient Descent and the Power Method: Exploiting their connection to find the leftmost eigen-pair and escape saddle points

2022-11-02 · Rachael Tappenden, Martin Takáč

This work shows that applying Gradient Descent (GD) with a fixed step size to minimize a (possibly nonconvex) quadratic function is equivalent to running the Power Method (PM) on the gradients. The connection between GD …

Optimistic and Adaptive Lagrangian Hedging

2021-01-23 · Ryan D'Orazio, Ruitong Huang

In online learning an algorithm plays against an environment with losses possibly picked by an adversary at each round. The generality of this framework includes problems that are not adversarial, for example offline opt…

Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize

2021-10-28 · Ryan D'Orazio, Nicolas Loizou, Issam Laradji, Ioannis Mitliagkas

We investigate the convergence of stochastic mirror descent (SMD) under interpolation in relatively smooth and smooth convex optimization. In relatively smooth convex optimization we provide new convergence guarantees fo…

Glocal Smoothness: Line Search can really help!

2025-06-14 · Curtis Fox, Aaron Mishkin, Sharan Vaswani, Mark Schmidt

Iteration complexities for first-order optimization algorithms are typically stated in terms of a global Lipschitz constant of the gradient, and near-optimal results are achieved using fixed step sizes. But many objectiv…

Adaptive Step Size Incremental Conductance Based Maximum Power Point Tracking (MPPT)

2020-11-15

Extracting maximum power available from photovoltaic arrays requires the system operating at the maximum power point (MPP). Therefore, finding the MPP is necessary for efficient operation of PV arrays. The MPP changes wi…

Point Tracking