Search Results for author:
Found 33 papers, 17 papers with code
Learning to Embed Multi-Modal Contexts for Situated Conversational Agents
The Situated Interactive Multi-Modal Conversations (SIMMC) 2. 0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i. e. visual appearances of objects and user utterances.
Debiasing Pre-Trained Language Models via Efficient Fine-Tuning
An explosion in the popularity of transformer-based language models (such as GPT-3, BERT, RoBERTa, and ALBERT) has opened the doors to new machine learning applications involving language modeling, text generation, and more.
Improving Fair Training under Correlation Shifts
First, we analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness.
Optimizing DDPM Sampling with Shortcut Fine-Tuning
In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs).
Looped Transformers as Programmable Computers
We present a framework for using transformer networks as universal computers by programming them with specific weights and placing them in a loop.
Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Specifically, we prove that the Wasserstein distance is upper bounded by the square root of the objective function up to multiplicative constants and a fixed constant offset.
Equal Improvability: A New Fairness Notion Considering the Long-term Impact
In order to promote long-term fairness, we propose a new fairness notion called Equal Improvability (EI), which equalizes the potential acceptance rate of the rejected samples across different groups assuming a bounded level of effort will be spent by each rejected sample.
Outlier-Robust Group Inference via Gradient Space Clustering
Traditional machine learning models focus on achieving good performance on the overall training distribution, but they often underperform on minority groups.
A Better Way to Decay: Proximal Gradient Training Algorithms for Neural Nets
For neural networks with ReLU activations, solutions to the weight decay objective are equivalent to those of a different objective in which the regularization term is instead a sum of products of $\ell_2$ (not squared) norms of the input and output weights associated each ReLU.
LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks
LIFT does not make any changes to the model architecture or loss function, and it solely relies on the natural language interface, enabling "no-code machine learning with LMs."
Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods.
Breaking Fair Binary Classification with Optimal Flipping Attacks
Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier.
Rare Gems: Finding Lottery Tickets at Initialization
Frankle & Carbin conjecture that we can avoid this by training "lottery tickets", i. e., special sparse subnetworks found at initialization, that can be trained to high accuracy.
Improved Input Reprogramming for GAN Conditioning
Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm.
GenLabel: Mixup Relabeling using Generative Models
Mixup is a data augmentation method that generates new data points by mixing a pair of input data.
Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
For this reason, data-centric approaches are crucial for the automation of machine learning operation pipeline.
Improving Fairness via Federated Learning
We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse than that of a fair classifier trained on centralized data.
Gradient Inversion with Generative Image Prior
Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients devices to preserve privacy, and the server trains models on the data via accessing only the gradients of those local data.
Sample Selection for Fair and Robust Training
In this work, we propose a sample selection-based algorithm for fair and robust training.
Coded-InvNet for Resilient Prediction Serving Systems
Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures.
Permutation-Based SGD: Is Random Optimal?
However, for general strongly convex functions, random permutations are optimal.
FairBatch: Batch Selection for Model Fairness
We address this problem via the lens of bilevel optimization.
SLM: Learning a Discourse Language Representation with Sentence Unshuffling
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner.
Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
The techniques usually require choosing a static compression ratio, often requiring users to balance the trade-off between model accuracy and per-iteration speedup.
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training.
Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
Ahn et al. (2018) firstly characterized the optimal sample complexity in the presence of graph side information, but the results are limited due to strict, unrealistic assumptions made on the unknown latent preference matrix and the structure of user clusters.
FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning.
FR-GAN: Fair and Robust Training
We consider the problem of fair and robust model training in the presence of data poisoning.
Binary Rating Estimation with Graph Side Information
Considering a simple correlation model between a rating matrix and a graph, we characterize the sharp threshold on the number of observed entries required to recover the rating matrix (called the optimal sample complexity) as a function of the quality of graph side information (to be detailed).
Hypergraph Spectral Clustering in the Weighted Stochastic Block Model
Our main contribution lies in performance analysis of the poly-time algorithms under a random hypergraph model, which we name the weighted stochastic block model, in which objects and multi-way measures are modeled as nodes and weights of hyperedges, respectively.
Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings
Recently, Shrivastava et al. (2017) propose Simulated+Unsupervised (S+U) learning: It first learns a mapping from synthetic data to real data, translates a large amount of labeled synthetic data to the ones that resemble real data, and then trains a learning model on the translated data.
Community Recovery in Hypergraphs
The objective of the problem is to cluster data points into distinct communities based on a set of measurements, each of which is associated with the values of a certain number of data points.
Speeding Up Distributed Machine Learning Using Codes
We focus on two of the most basic building blocks of distributed learning algorithms: matrix multiplication and data shuffling.
