arXiv subjects

Yi Sun

Publications and source records attributed to Yi Sun.

At least 109 records · Page 6Linked to original sources

arXiv2023

AdaSelection: Accelerating Deep Learning Training through Data Subsampling

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance. Our method is able to flexibly combines an arbitrary number of baseline sub-sampling methods incorporating the method-level importance and intra-method sample-level importance at each iteration. The standard practice of ad-hoc sampling often leads to continuous training with vast amounts of data from production environments. To improve the selection of data instances during forward and backward passes, we propose recording a constant amount of information per instance from these passes. We demonstrate the effectiveness of our method by testing it across various types of inputs and tasks, including the classification tasks on both image and language datasets, as well as regression tasks. Compared with industry-standard baselines, AdaSelection consistently displays superior performance.

cs.LG↗

arXiv2023

Certifying Zero-Knowledge Circuits with Refinement Types

Zero-knowledge (ZK) proof systems have emerged as a promising solution for building security-sensitive applications. However, bugs in ZK applications are extremely difficult to detect and can allow a malicious party to silently exploit the system without leaving any observable trace. This paper presents Coda, a novel statically-typed language for building zero-knowledge applications. Critically, Coda makes it possible to formally specify and statically check properties of a ZK application through a rich refinement type system. One of the key challenges in formally verifying ZK applications is that they require reasoning about polynomial equations over large prime fields that go beyond the capabilities of automated theorem provers. Coda mitigates this challenge by generating a set of Coq lemmas that can be proven in an interactive manner with the help of a tactic library. We have used Coda to re-implement 79 arithmetic circuits from widely-used Circom libraries and applications. Our evaluation shows that Coda makes it possible to specify important and formally verify correctness properties of these circuits. Our evaluation also revealed 6 previously-unknown vulnerabilities in the original Circom projects.

cs.CR↗

arXiv2023

Boundary-to-Solution Mapping for Groundwater Flows in a Toth Basin

In this paper, the authors propose a new approach to solving the groundwater flow equation in the Toth basin of arbitrary top and bottom topographies using deep learning. Instead of using traditional numerical solvers, they use a DeepONet to produce the boundary-to-solution mapping. This mapping takes the geometry of the physical domain along with the boundary conditions as inputs to output the steady state solution of the groundwater flow equation. To implement the DeepONet, the authors approximate the top and bottom boundaries using truncated Fourier series or piecewise linear representations. They present two different implementations of the DeepONet: one where the Toth basin is embedded in a rectangular computational domain, and another where the Toth basin with arbitrary top and bottom boundaries is mapped into a rectangular computational domain via a nonlinear transformation. They implement the DeepONet with respect to the Dirichlet and Robin boundary condition at the top and the Neumann boundary condition at the impervious bottom boundary, respectively. Using this deep-learning enabled tool, the authors investigate the impact of surface topography on the flow pattern by both the top surface and the bottom impervious boundary with arbitrary geometries. They discover that the average slope of the top surface promotes long-distance transport, while the local curvature controls localized circulations. Additionally, they find that the slope of the bottom impervious boundary can seriously impact the long-distance transport of groundwater flows. Overall, this paper presents a new and innovative approach to solving the groundwater flow equation using deep learning, which allows for the investigation of the impact of surface topography on groundwater flow patterns.

physics.geo-ph↗

arXiv2022

The role of steric effects on hydrogen atom transfer reactions

We explored how steric effects influence the rate of hydrogen atom transfer (HAT) reactions between oxyradicals and alkanes. Quantum chemical computations of transition states show that activation barriers and reaction enthalpies are both influenced by bulky substituents on the radical, but less so by substituents on the alkane. The activation barriers correlate with reaction enthalpies via the Evans-Polanyi relationship, even when steric effects are important. Dispersion effects can additionally stabilize transition states in some cases.

physics.chem-ph↗

arXiv2022

FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Data

Today, recommender systems have played an increasingly important role in shaping our experiences of digital environments and social interactions. However, as recommender systems become ubiquitous in our society, recent years have also witnessed significant fairness concerns for recommender systems. Specifically, studies have shown that recommender systems may inherit or even amplify biases from historical data, and as a result, provide unfair recommendations. To address fairness risks in recommender systems, most of the previous approaches to date are focused on modifying either the existing training data samples or the deployed recommender algorithms, but unfortunately with limited degrees of success. In this paper, we propose a new approach called fair recommendation with optimized antidote data (FairRoad), which aims to improve the fairness performances of recommender systems through the construction of a small and carefully crafted antidote dataset. Toward this end, we formulate our antidote data generation task as a mathematical optimization problem, which minimizes the unfairness of the targeted recommender systems while not disrupting the deployed recommendation algorithms. Extensive experiments show that our proposed antidote data generation algorithm significantly improve the fairness of recommender systems with a small amounts of antidote data.

cs.IR↗

arXiv2022

Artificial Intelligence Security Competition (AISC)

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

cs.CR↗

arXiv2022

ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation

Over the past few years, AI methods of generating images have been increasing in capabilities, with recent breakthroughs enabling high-resolution, photorealistic "deepfakes" (artificially generated images with the purpose of misinformation or harm). The rise of deepfakes has potential for social disruption. Recent work has proposed using ZK-SNARKs (zero-knowledge succinct non-interactive argument of knowledge) and attested cameras to verify that images were taken by a camera. ZK-SNARKs allow verification of image transformations non-interactively (i.e., post-hoc) with only standard cryptographic hardness assumptions. Unfortunately, this work does not preserve input privacy, is impractically slow (working only on 128$\times$128 images), and/or requires custom cryptographic arguments. To address these issues, we present zk-img, a library for attesting to image transformations while hiding the pre-transformed image. zk-img allows application developers to specify high level image transformations. Then, zk-img will transparently compile these specifications to ZK-SNARKs. To hide the input or output images, zk-img will compute the hash of the images inside the ZK-SNARK. We further propose methods of chaining image transformations securely and privately, which allows for arbitrarily many transformations. By combining these optimizations, zk-img is the first system to be able to transform HD images on commodity hardware, securely and privately.

cs.CR↗

arXiv2022

Rod and slit photonic crystal microrings for on-chip cavity quantum electrodynamics

Micro-/nanocavities that combine high quality factor ($Q$) and small mode volume ($V$) have been used to enhance light-matter interactions for cavity quantum electrodynamics (cQED). Whispering gallery mode (WGM) geometries such as microdisks and microrings support high-$Q$ and are design- and fabrication-friendly, but $V$ is often limited to tens of cubic wavelengths to avoid WGM radiation. The stronger modal confinement provided by either one-dimensional or two-dimensional photonic crystal defect geometries can yield sub-cubic-wavelength $V$, yet the requirements on precise design and dimensional control are typically much more stringent to ensure high-$Q$. Given their complementary features, there has been sustained interest in geometries that combine the advantages of WGM and photonic crystal cavities. Recently, a `microgear' photonic crystal ring (MPhCR) has shown promise in enabling additional defect localization ($>$ 10$\times$ reduction of $V$) of a WGM, while maintaining high-$Q$ ($\approx10^6$) and other WGM characteristics in ease of coupling and design. However, the unit cell geometry used is unlike traditional PhC cavities, and etched surfaces may be too close to embedded quantum nodes (quantum dots, atomic defect spins, etc.) for cQED applications. Here, we report two novel PhCR designs with `rod' and `slit' unit cells, whose geometries are more traditional and suitable for solid-state cQED. Both rod and slit PhCRs have high-$Q$ ($>10^6$) with WGM coupling properties preserved. A further $\approx$~10$\times$ reduction of $V$ by defect localization is observed in rod PhCRs. Moreover, both fundamental and 2nd-order PhC modes co-exist in slit PhCRs with high $Q$s and good coupling. Our work showcases that high-$Q/V$ PhCRs are in general straightforward to design and fabricate and are a promising platform to explore for cQED.

physics.optics↗

arXiv2022

NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction

Using prompts to utilize language models to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm. Nonetheless, virtually all prompt-based methods are token-level, meaning they all utilize GPT's left-to-right language model or BERT's masked language model to perform cloze-style tasks. In this paper, we attempt to accomplish several NLP tasks in the zero-shot scenario using a BERT original pre-training task abandoned by RoBERTa and other models--Next Sentence Prediction (NSP). Unlike token-level techniques, our sentence-level prompt-based method NSP-BERT does not need to fix the length of the prompt or the position to be predicted, allowing it to handle tasks such as entity linking with ease. Based on the characteristics of NSP-BERT, we offer several quick building templates for various downstream tasks. We suggest a two-stage prompt method for word sense disambiguation tasks in particular. Our strategies for mapping the labels significantly enhance the model's performance on sentence pair tasks. On the FewCLUE benchmark, our NSP-BERT outperforms other zero-shot methods on most of these tasks and comes close to the few-shot methods.

cs.CL↗

arXiv2022

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

As ML models have increased in capabilities and accuracy, so has the complexity of their deployments. Increasingly, ML model consumers are turning to service providers to serve the ML models in the ML-as-a-service (MLaaS) paradigm. As MLaaS proliferates, a critical requirement emerges: how can model consumers verify that the correct predictions were served, in the face of malicious, lazy, or buggy service providers? In this work, we present the first practical ImageNet-scale method to verify ML model inference non-interactively, i.e., after the inference has been done. To do so, we leverage recent developments in ZK-SNARKs (zero-knowledge succinct non-interactive argument of knowledge), a form of zero-knowledge proofs. ZK-SNARKs allows us to verify ML model execution non-interactively and with only standard cryptographic hardness assumptions. In particular, we provide the first ZK-SNARK proof of valid inference for a full resolution ImageNet model, achieving 79\% top-5 accuracy. We further use these ZK-SNARKs to design protocols to verify ML model execution in a variety of scenarios, including for verifying MLaaS predictions, verifying MLaaS model accuracy, and using ML models for trustless retrieval. Together, our results show that ZK-SNARKs have the promise to make verified ML model inference practical.

cs.CR↗

arXiv2022

Enhanced sampling reveals the main pathway of an organic cascade reaction

Normal molecular dynamics simulations are usually unable to simulate chemical reactions due to the low probability of forming the transition state. Therefore, enhanced sampling methods are implemented to accelerate the occurrence of chemical reactions. In this investigation, we present an application of metadynamics in simulating an organic multi-step cascade reaction. The analysis of the reaction trajectory reveals the barrier heights of both forward and reverse reactions. We also present a discussion of the advantages and disadvantages of generating the reactive pathway using molecular dynamics and the intrinsic reaction coordinate (IRC) algorithm.

physics.chem-ph↗

arXiv2022

Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM

Motivated by applications to single-particle cryo-electron microscopy (cryo-EM), we study several problems of function estimation in a high noise regime, where samples are observed after random rotation and possible linear projection of the function domain. We describe a stratification of the Fisher information eigenvalues according to transcendence degrees of graded pieces of the algebra of group invariants, and we relate critical points of the log-likelihood landscape to a sequence of moment optimization problems, extending previous results for a discrete rotation group without projections. We then compute the transcendence degrees and forms of these optimization problems for several examples of function estimation under $SO(2)$ and $SO(3)$ rotations, including a simplified model of cryo-EM as introduced by Bandeira, Blum-Smith, Kileel, Perry, Weed, and Wein. We affirmatively resolve conjectures that $3^\text{rd}$-order moments are sufficient to locally identify a generic signal up to its rotational orbit in these examples. For low-dimensional approximations of the electric potential maps of two small protein molecules, we empirically verify that the noise-scalings of the Fisher information eigenvalues conform with our theoretical predictions over a range of SNR, in a model of $SO(3)$ rotations without projections.

math.ST↗

arXiv2022

TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance

Grasp pose estimation is an important issue for robots to interact with the real world. However, most of existing methods require exact 3D object models available beforehand or a large amount of grasp annotations for training. To avoid these problems, we propose TransGrasp, a category-level grasp pose estimation method that predicts grasp poses of a category of objects by labeling only one object instance. Specifically, we perform grasp pose transfer across a category of objects based on their shape correspondences and propose a grasp pose refinement module to further fine-tune grasp pose of grippers so as to ensure successful grasps. Experiments demonstrate the effectiveness of our method on achieving high-quality grasps with the transferred grasp poses. Our code is available at https://github.com/yanjh97/TransGrasp.

cs.RO↗

arXiv2022

Accelerated Kinetic Monte Carlo methods for general nonlocal traffic flow models

This paper presents a class of one-dimensional cellular automata (CA) models on traffic flows, featuring nonlocal look-ahead interactions. We develop kinetic Monte Carlo (KMC) algorithms to simulate the dynamics. The standard KMC method can be inefficient for models with global interactions. We design an accelerated KMC method to reduce the computational complexity in the evaluation of the nonlocal transition rates. We investigate several numerical experiments to demonstrate the efficiency of the accelerated algorithm, and obtain the fundamental diagrams of the dynamics under various parameter settings.

math.NA↗

arXiv2022

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI

Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue microstructure based on biophysical models, which are complex and highly non-linear. Resolving microstructures with optimization techniques is prone to estimation errors and requires dense sampling in the q-space. Deep learning based approaches have been proposed to overcome these limitations. Motivated by the superior performance of the Transformer, in this work, we present a learning-based framework based on Transformer, namely, a Microstructure Estimation Transformer with Sparse Coding (METSC) for dMRI-based microstructure estimation with downsampled q-space data. To take advantage of the Transformer while addressing its limitation in large training data requirements, we explicitly introduce an inductive bias - model bias into the Transformer using a sparse coding technique to facilitate the training process. Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage. The embedding stage is a Transformer-based structure that encodes the signal to ensure the voxel is represented effectively. In the sparse representation stage, a dictionary is constructed by solving a sparse reconstruction problem that unfolds the Iterative Hard Thresholding (IHT) process. The mapping stage is essentially a decoder that computes the microstructural parameters from the output of the second stage, based on the weighted sum of normalized dictionary coefficients where the weights are also learned. We tested our framework on two dMRI models with downsampled q-space data, including the intravoxel incoherent motion (IVIM) model and the neurite orientation dispersion and density imaging (NODDI) model. The proposed method achieved up to 11.25 folds of acceleration in scan time and outperformed the other state-of-the-art learning-based methods.

eess.SP↗

arXiv2022

Using Natural Sentences for Understanding Biases in Language Models

Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need for a prompt-style dataset to trigger specific behaviors of language models. In this paper, we address this gap by creating a prompt dataset with respect to occupations collected from real-world natural sentences present in Wikipedia. We aim to understand the differences between using template-based prompts and natural sentence prompts when studying gender-occupation biases in language models. We find bias evaluations are very sensitive to the design choices of template prompts, and we propose using natural sentence prompts for systematic evaluations to step away from design choices that could introduce bias in the observations.

cs.CL↗

arXiv2022

Complex analysis of divergent perturbation theory at finite temperature

We investigate the convergence properties of finite-temperature perturbation theory by considering the mathematical structure of thermodynamic potentials using complex analysis. We discover that zeros of the partition function lead to poles in the internal energy and logarithmic singularities in the Helmholtz free energy which create divergent expansions in the canonical ensemble. Analysing these zeros reveals that the radius of convergence increases for higher temperatures. In contrast, when the reference state is degenerate, these poles in the internal energy create a zero radius of convergence in the zero-temperature limit. Finally, by showing that the poles in the internal energy reduce to exceptional points in the zero-temperature limit, we unify the two main mathematical representations of quantum phase transitions.

physics.chem-ph↗

arXiv2021

CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and recommendation. In this paper, we propose the Cross-Modality Attention Contrastive Language-Image Pre-training (CMA-CLIP), a new framework which unifies two types of cross-modality attentions, sequence-wise attention and modality-wise attention, to effectively fuse information from image and text pairs. The sequence-wise attention enables the framework to capture the fine-grained relationship between image patches and text tokens, while the modality-wise attention weighs each modality by its relevance to the downstream tasks. In addition, by adding task specific modality-wise attentions and multilayer perceptrons, our proposed framework is capable of performing multi-task classification with multi-modalities. We conduct experiments on a Major Retail Website Product Attribute (MRWPA) dataset and two public datasets, Food101 and Fashion-Gen. The results show that CMA-CLIP outperforms the pre-trained and fine-tuned CLIP by an average of 11.9% in recall at the same level of precision on the MRWPA dataset for multi-task classification. It also surpasses the state-of-the-art method on Fashion-Gen Dataset by 5.5% in accuracy and achieves competitive performance on Food101 Dataset. Through detailed ablation studies, we further demonstrate the effectiveness of both cross-modality attention modules and our method's robustness against noise in image and text inputs, which is a common challenge in practice.

cs.CV↗