Search Results for author:
Found 20 papers, 8 papers with code
Directly Fine-Tuning Diffusion Models on Differentiable Rewards
We present Direct Reward Fine-Tuning (DRaFT), a simple and effective method for fine-tuning diffusion models to maximize differentiable reward functions, such as scores from human preference models.
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
We propose an evolution strategies-based algorithm for estimating gradients in unrolled computation graphs, called ES-Single.
On Implicit Bias in Overparameterized Bilevel Optimization
Bilevel problems consist of two nested sub-problems, called the outer and inner problems, respectively.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Amortized Proximal Optimization
Using APO to adapt a structured preconditioning matrix generally results in optimization performance competitive with second-order methods.
Disentanglement and Generalization Under Correlation Shifts
Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e. g., they may change between domains, datasets, or applications) and models that exploit them do not generalize when correlations shift.
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
Unrolled computation graphs arise in many scenarios, including training RNNs, tuning hyperparameters through unrolled optimization, and training learned optimizers.
Lyapunov Exponents for Diversity in Differentiable Games
We generalize this idea to non-conservative, multi-agent gradient systems by proposing a method - denoted Generalized Ridge Rider (GRR) - for finding arbitrary bifurcation points.
Complex Momentum for Optimization in Games
We generalize gradient descent with momentum for optimization in differentiable games to have complex-valued momentum.
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
For problems where global invertibility is necessary, such as applying normalizing flows on OOD data, we show the importance of designing stable INN building blocks.
Optimizing Millions of Hyperparameters by Implicit Differentiation
We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations.
Out-of-distribution Detection in Few-shot Classification
In this work, we propose tasks for out-of-distribution detection in the few-shot setting and establish benchmark datasets, based on four popular few-shot classification datasets.
On the Invertibility of Invertible Neural Networks
Guarantees in deep learning are hard to achieve due to the interplay of flexible modeling schemes and complex tasks.
Online Hyperparameter Adaptation via Amortized Proximal Optimization
Effective performance of neural networks depends critically on effective tuning of optimization hyperparameters, especially learning rates (and schedules thereof).
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
Empirically, our approach outperforms competing hyperparameter optimization methods on large-scale deep learning problems.
Reversible Recurrent Neural Networks
Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory requirements of training, as hidden states need not be stored and instead can be recomputed during backpropagation.
Distilling the Posterior in Bayesian Neural Networks
We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN).
Adversarial Distillation of Bayesian Neural Network Posteriors
We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN).
Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies.
MovieGraphs: Towards Understanding Human-Centric Situations from Videos
Towards this goal, we introduce a novel dataset called MovieGraphs which provides detailed, graph-based annotations of social situations depicted in movie clips.
