arXiv subjects

Yuri Grinberg

Publications and source records attributed to Yuri Grinberg.

8 recordsLinked to original sources

arXiv2026

Gen-Fab: A Variation-Aware Generative Model for Predicting Fabrication Variations in Nanophotonic Devices

Silicon photonic devices often exhibit fabrication-induced variations such as over-etching, underetching, and corner rounding, which can significantly alter device performance. These variations are non-uniform and are influenced by feature size and shape. Accurate digital twins are therefore needed to predict the range of possible fabricated outcomes for a given design. In this paper, we introduce Gen-Fab, a conditional generative adversarial network (cGAN) based on Pix2Pix to predict and model uncertainty in photonic fabrication outcomes. The proposed method takes a design layout (in GDS format) as input and produces diverse high-resolution predictions similar to scanning electron microscope (SEM) images of fabricated devices, capturing the range of process variations at the nanometer scale. To enable one-to-many mapping, we inject a latent noise vector at the model bottleneck. We compare Gen-Fab against three baselines: (1) a deterministic U-Net predictor, (2) an inference-time Monte Carlo Dropout U-Net, and (3) an ensemble of varied U-Nets. Evaluations on an out-of-distribution dataset of fabricated photonic test structures demonstrate that Gen-Fab outperforms all baselines in both accuracy and uncertainty modeling. An additional distribution shift analysis further confirms its strong generalization to unseen fabrication geometries. Gen-Fab achieves the highest intersection-over-union (IoU) score of 89.8%, outperforming the deterministic U-Net (85.3%), the MC-Dropout U-Net (83.4%), and varying U-Nets (85.8%). It also better aligns with the distribution of real fabrication outcomes, achieving lower Kullback-Leibler divergence and Wasserstein distance.

cs.CV↗

arXiv2024

Perfectly vertical silicon metamaterial grating couplers with large segmentation periods up to 650 nm

Perfectly vertical grating couplers leveraging metamaterials can achieve both high coupling efficiency and minimal back reflection. The fabricability of these designs, with segmentations in both the longitudinal and transverse dimensions, hinges on the minimum feature size offered by cutting-edge fabrication technologies. In this work we present both numerical and experimental evidence that high performance devices can be obtained while using large transverse segmentation periods of up to 650 nm, thereby increasing the critical feature sizes. For single-step etched couplers produced on the 220 nm silicon-on-insulator platform, we demonstrate coupling efficiencies of nearly 50% in the C-band and remarkably low back reflections of -22 dB at zero-degree incidence angle. Notably, the duty cycles used in our optimized designs deviate significantly from those predicted by traditional effective medium models, even for small periods. Our findings promise to expand the range of optical properties achievable in metamaterials and offer fresh insights into the fine-tuning of nanophotonic devices.

physics.optics↗

arXiv2023

Optical wavefront phase-tilt measurement using Si-photonic waveguide grating couplers

Silicon photonic wavefront phase-tilt sensors for wavefront monitoring using surface coupling grating arrays are demonstrated. The first design employs the intrinsic angle dependence of the grating coupling efficiency to determine local wavefront tilt, with a measured sensitivity of 7 dB/degree. A second design connects four gratings in an interferometric waveguide circuit to determine incident wavefront phase variation across the sensor area. In this device, one fringe spacing corresponds to approximately 2 degree wavefront tilt change. These sensor elements can sample a wavefront incident on the chip surface without the use of bulk optic elements, fiber arrays, or imaging arrays. Both sensor elements are less than 60 um across, and can be combined into larger arrays to monitor wavefront tilt and distortion across an image or pupil plane in adaptive optics systems for free space optical communications, astronomy and beam pointing applications.

physics.optics↗

arXiv2023

Improving Fabrication Fidelity of Integrated Nanophotonic Devices Using Deep Learning

Next-generation integrated nanophotonic device designs leverage advanced optimization techniques such as inverse design and topology optimization which achieve high performance and extreme miniaturization by optimizing a massively complex design space enabled by small feature sizes. However, unless the optimization is heavily constrained, the generated small features are not reliably fabricated, leading to optical performance degradation. Even for simpler, conventional designs, fabrication-induced performance degradation still occurs. The degree of deviation from the original design not only depends on the size and shape of its features, but also on the distribution of features and the surrounding environment, presenting complex, proximity-dependent behavior. Without proprietary fabrication process specifications, design corrections can only be made after calibrating fabrication runs take place. In this work, we introduce a general deep machine learning model that automatically corrects photonic device design layouts prior to first fabrication. Only a small set of scanning electron microscopy images of engineered training features are required to create the deep learning model. With correction, the outcome of the fabricated layout is closer to what is intended, and thus so too is the performance of the design. Without modifying the nanofabrication process, adding significant computation in design, or requiring proprietary process specifications, we believe our model opens the door to new levels of reliability and performance in next-generation photonic circuits.

cs.LG↗

arXiv2022

PCA-Boosted Autoencoders for Nonlinear Dimensionality Reduction in Low Data Regimes

Autoencoders (AE) provide a useful method for nonlinear dimensionality reduction but are ill-suited for low data regimes. Conversely, Principal Component Analysis (PCA) is data-efficient but is limited to linear dimensionality reduction, posing a problem when data exhibits inherent nonlinearity. This presents a challenge in various scientific and engineering domains such as the nanophotonic component design, where data exhibits nonlinear features while being expensive to obtain due to costly real measurements or resource-consuming solutions of partial differential equations. To address this difficulty, we propose a technique that harnesses the best of both worlds: an autoencoder that leverages PCA to perform well on scarce nonlinear data. Specifically, we outline a numerically robust PCA-based initialization of AE, which, together with the parameterized ReLU activation function, allows the training process to start from an exact PCA solution and improve upon it. A synthetic example is presented first to study the effects of data nonlinearity and size on the performance of the proposed method. We then evaluate our method on several nanophotonic component design problems where obtaining useful data is expensive. To demonstrate universality, we also apply it to tasks in other scientific domains: a benchmark breast cancer dataset and a gene expression dataset. We show that our proposed approach is substantially better than both PCA and randomly initialized AE in the majority of low-data regime cases we consider, or at least is comparable to the best of either of the other two methods.

cs.LG↗

arXiv2020

Design of Compact and Efficient Silicon Photonic Micro Antennas with Perfectly Vertical Emission

Compact and efficient optical antennas are fundamental components for many applications, including high-density fiber-chip coupling and optical phased arrays. Here we present the design of grating-based micro-antennas with perfectly vertical emission in the 300-nm silicon-on-insulator platform. We leverage a methodology combining adjoint optimization and machine learning dimensionality reduction to efficiently map the multiparameter design space of the antennas, analyse a large number of relevant performance metrics, carry out the required multi-objective optimization, and discover high performance designs. Using a one-step apodized grating we achieve a vertical upward diffraction efficiency of almost 92% with a 3.6 μm-long antenna. When coupled with an ultra-high numerical aperture fiber, the antenna exhibits a coupling efficiency of more than 81% (-0.9 dB) and a 1-dB bandwidth of almost 158 nm. The reflection generated by the perfectly vertical antenna is smaller than -20 dB on a 200-nm bandwidth centered at λ = 1550 nm.

physics.optics↗

arXiv2019

Mapping the global design space of nanophotonic components using machine learning pattern recognition

Nanophotonics finds ever broadening applications requiring complex component designs with a large number of parameters to be simultaneously optimized. Recent methodologies employing optimization algorithms commonly focus on a single design objective, provide isolated designs, and do not describe how the design parameters influence the device behaviour. Here we propose and demonstrate a machine-learning-based approach to map and characterize the multi-parameter design space of nanophotonic components. Pattern recognition is used to reveal the relationship between an initial sparse set of optimized designs through a significant reduction in the number of characterizing parameters. This defines a design sub-space of lower dimensionality that can be mapped faster by orders of magnitude than the original design space. As a result, multiple performance criteria are clearly visualized, revealing the interplay of the design parameters, highlighting performance and structural limitations, and inspiring new design ideas. This global perspective on high-dimensional design problems represents a major shift in how modern nanophotonic design is approached and provides a powerful tool to explore complexity in next-generation devices.

physics.app-ph↗

arXiv2012

Bellman Error Based Feature Generation using Random Projections on Sparse Spaces

We address the problem of automatic generation of features for value function approximation. Bellman Error Basis Functions (BEBFs) have been shown to improve the error of policy evaluation with function approximation, with a convergence rate similar to that of value iteration. We propose a simple, fast and robust algorithm based on random projections to generate BEBFs for sparse feature spaces. We provide a finite sample analysis of the proposed method, and prove that projections logarithmic in the dimension of the original space are enough to guarantee contraction in the error. Empirical results demonstrate the strength of this method.

cs.LG↗