Search Results for author:
Found 14 papers, 8 papers with code
EvalGIM: A Library for Evaluating Generative Image Models
To enable actionable evaluation insights, we introduce ''Evaluation Exercises'' that highlight takeaways for specific evaluation questions.
Transformers Can Navigate Mazes With Multi-Step Prediction
We train parameter-matched transformers from scratch, under identical settings, to navigate mazes of varying types and sizes with standard next token prediction and MLM-U, an objective explicitly predicting multiple steps ahead and backwards.
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
Today's best language models still struggle with hallucinations: factually incorrect generations, which impede their ability to reliably retrieve information seen during training.
DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable.
Benchmarking Neural Network Training Algorithms
In order to address these challenges, we introduce a new, competitive, time-to-result benchmark using multiple workloads running on fixed hardware, the AlgoPerf: Training Algorithms benchmark.
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model.
Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity
Federated learning (FL) is an effective mechanism for data privacy in recommender systems by running machine learning model training on-device.
Privacy-Aware Compression for Federated Data Analysis
Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of distributed low-bandwidth user devices to estimate aggregate statistics.
Papaya: Practical, Private, and Scalable Federated Learning
Our work tackles the aforementioned issues, sketches of some of the system design challenges and their solutions, and touches upon principles that emerged from building a production FL system for millions of clients.
Sustainable AI: Environmental Implications, Challenges and Opportunities
This paper explores the environmental impact of the super-linear growth trends for AI from a holistic perspective, spanning Data, Algorithms, and System Hardware.
Trade-offs of Local SGD at Scale: An Empirical Study
As datasets and models become increasingly large, distributed training has become a necessary component to allow deep neural networks to train in reasonable amounts of time.
Learning with Gradient Descent and Weakly Convex Losses
Out of sample guarantees are then achieved by decomposing the test error into generalisation, optimisation and approximation errors, each of which can be bounded and traded off with respect to algorithmic parameters, sample size and magnitude of this eigenvalue.
CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery
The paper is the first to the extent of our knowledge to perform a data-driven, in-depth analysis of applying partial recovery to recommendation models and identified a trade-off between accuracy and performance.
MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions
This is largely an artifact of building on top of frameworks designed for RL in games (e. g. OpenAI Gym).
