Search Results for author:
Found 57 papers, 19 papers with code
Analyzing the effect of neural network architecture on training performance
Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training.
Randomization Techniques to Mitigate the Risk of Copyright Infringement
In this paper, we investigate potential randomization approaches that can complement current practices of input-based methods (such as licensing data and prompt filtering) and output-based methods (such as recitation checker, license checker, and model-based similarity score) for copyright protection.
A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs
Our BLT-DP-FTRL maintains the ease-of-use advantages of tree aggregation, while essentially matching matrix factorization in terms of utility and privacy.
Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
We study $L_2$ mean estimation under central differential privacy and communication constraints, and address two key challenges: firstly, existing mean estimation schemes that simultaneously handle both constraints are usually optimized for $L_\infty$ geometry and rely on random rotation or Kashin's representation to adapt to $L_2$ geometry, resulting in suboptimal leading constants in mean square errors (MSEs); secondly, schemes achieving order-optimal communication-privacy trade-offs do not extend seamlessly to streaming differential privacy (DP) settings (e. g., tree aggregation or matrix factorization), rendering them incompatible with DP-FTRL type optimizers.
Prompt Public Large Language Models to Synthesize Data for Private On-device Applications
Pre-training on public data is an effective method to improve the performance for federated learning (FL) with differential privacy (DP).
Efficient Language Model Architectures for Differentially Private Federated Learning
Cross-device federated learning (FL) is a technique that trains a model on data distributed across typically millions of edge devices without data leaving the devices.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #1 on
Zero-Shot Video Question Answer
on Video-MME
Enhancing Kubernetes Automated Scheduling with Deep Learning and Reinforcement Techniques for Large-Scale Cloud Computing Optimization
With the continuous expansion of the scale of cloud computing applications, artificial intelligence technologies such as Deep Learning and Reinforcement Learning have gradually become the key tools to solve the automated task scheduling of large-scale cloud computing systems.
Privacy-Preserving Instructions for Aligning Large Language Models
Service providers of large language model (LLM) applications collect user instructions in the wild and use them in further aligning LLMs with users' intentions.
PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter
Our research undertakes a thorough exploration of the state-of-the-art perceiver resampler architecture and builds a strong baseline.
Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models
Foundation models (FMs) adapt well to specific domains or tasks with fine-tuning, and federated learning (FL) enables the potential for privacy-preserving fine-tuning of the FMs with on-device local data.
InstructPipe: Building Visual Programming Pipelines with Human Instructions
Our user study (N=16) showed that InstructPipe empowers novice users to streamline their workflow in creating desired ML pipelines, reduce their learning curve, and spark innovative ideas with open-ended commands.
Analyze Drivers' Intervention Behavior During Autonomous Driving -- A VR-incorporated Approach
Given the rapid advance in ITS technologies, future mobility is pointing to vehicular autonomy.
User Inference Attacks on Large Language Models
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications.
Federated Learning of Gboard Language Models with Differential Privacy
We train language models (LMs) with federated learning (FL) and differential privacy (DP) in the Google Keyboard (Gboard).
Can Public Large Language Models Help Private Cross-device Federated Learning?
We study (differentially) private federated learning (FL) of language models.
An Empirical Evaluation of Federated Contextual Bandit Algorithms
As the adoption of federated learning increases for learning from sensitive data local to user devices, it is natural to ask if the learning can be done using implicit signals generated as users interact with the applications of interest, rather than requiring access to explicit labels which can be difficult to acquire in many tasks.
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
However, while some adoption of DP has happened in industry, attempts to apply DP to real world complex ML models are still few and far between.
On the Convergence of Federated Averaging with Cyclic Client Participation
Federated Averaging (FedAvg) and its variants are the most popular optimization algorithms in federated learning (FL).
Decentralized Energy Market Integrating Carbon Allowance Trade and Uncertainty Balance in Energy Communities
With the sustained attention on carbon neutrality, the personal carbon trading (PCT) scheme has been embraced as an auspicious paradigm for scaling down carbon emissions.
Learning to Generate Image Embeddings with User-level Differential Privacy
Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past.
Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition.
Ranked #1 on
Zero-Shot Action Recognition
on HMDB51
Beyond Uniform Lipschitz Condition in Differentially Private Optimization
Most prior results on differentially private stochastic gradient descent (DP-SGD) are derived under the simplistic assumption of uniform Lipschitzness, i. e., the per-sample gradients are uniformly bounded.
Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
To better answer these questions, we propose Motley, a benchmark for personalized federated learning.
On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data
Motivated by this observation, we propose a new quantity, average drift at optimum, to measure the effects of data heterogeneity, and explicitly use it to present a new theoretical analysis of FedAvg.
Digging into Primary Financial Market: Challenges and Opportunities of Adopting Blockchain
Since the emergence of blockchain technology, its application in the financial market has always been an area of focus and exploration by all parties.
Efficient and Private Federated Learning with Partially Trainable Networks
Through extensive experiments, we empirically show that Federated learning of Partially Trainable neural networks (FedPT) can result in superior communication-accuracy trade-offs, with up to $46\times$ reduction in communication cost, at a small accuracy cost.
Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions
Federated learning has been deployed to train machine learning models from decentralized client data on mobile devices in practice.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data
Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data.
Local Adaptivity in Federated Learning: Convergence and Consistency
Popular optimization algorithms of FL use vanilla (stochastic) gradient descent for both local updates at clients and global updates at the aggregating server.
Practical and Private (Deep) Learning without Sampling or Shuffling
We consider training models with differential privacy (DP) using mini-batch gradients.
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision.
Ranked #145 on
Image Classification
on CIFAR-10
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer
Further, we demonstrate that the compact structure and corresponding initialization from the Lottery Ticket Hypothesis can also help in data-free training.
Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training
Our adaptive networks also outperform larger widened non-adaptive architectures that have 1. 5 times more parameters.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
The Effect of Neural Net Architecture on Gradient Confusion & Training Performance
Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training.
Adversarial Training for Free!
Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks.
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
Our results show that, for popular initialization techniques, increasing the width of neural networks leads to lower gradient confusion, and thus faster model training.
Universal Adversarial Training
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels.
Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
Chest X-rays is one of the most commonly available and affordable radiological examinations in clinical practice.
Accurate and efficient video de-fencing using convolutional neural networks and temporal information
To overcome these problems, we propose a novel method consisting of segmentation using convolutional neural networks and a fast/robust recovery algorithm.
Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
We propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs.
The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image.
Learning to Cluster for Proposal-Free Instance Segmentation
We utilize the most fundamental property of instance labeling -- the pairwise relationship between pixels -- as the supervision to formulate the learning objective, then apply it to train a fully convolutional network (FCN) for learning to perform pixel-wise clustering.
Ranked #14 on
Lane Detection
on TuSimple
Visualizing the Loss Landscape of Neural Nets
Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions.
Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
There is an increasing interest on accelerating neural networks for real-time applications.
Group-driven Reinforcement Learning for Personalized mHealth Intervention
Due to the popularity of smartphones and wearable devices nowadays, mobile health (mHealth) technologies are promising to bring positive and wide impacts on people's health.
Adaptive Consensus ADMM for Distributed Optimization
The alternating direction method of multipliers (ADMM) is commonly used for distributed model fitting problems, but its performance and reliability depend strongly on user-defined penalty parameters.
Training Quantized Nets: A Deeper Understanding
Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.
Stabilizing Adversarial Nets With Prediction Methods
Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train.
Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation
Relaxed ADMM is a generalization of ADMM that often achieves better performance, but its efficiency depends strongly on algorithm parameters that must be chosen by an expert user.
Non-negative Factorization of the Occurrence Tensor from Financial Contracts
We propose an algorithm for the non-negative factorization of an occurrence tensor built from heterogeneous networks.
An Empirical Study of ADMM for Nonconvex Problems
The alternating direction method of multipliers (ADMM) is a common optimization tool for solving constrained and non-differentiable problems.
Adaptive ADMM with Spectral Penalty Parameter Selection
The alternating direction method of multipliers (ADMM) is a versatile tool for solving a wide range of constrained optimization problems, with differentiable or non-differentiable objective functions.
Training Neural Networks Without Gradients: A Scalable ADMM Approach
With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks.
Exploiting Lists of Names for Named Entity Identification of Financial Institutions from Unstructured Documents
To our knowledge, our proposed solutions, Dict-based NER and Rank-based ER, and the root and suffix dictionaries, are the first attempt to exploit specialized knowledge, i. e., lists of FI names, for rule-based NER and
