papers

Publications (22)

cs.LG2020

Finite Versus Infinite Neural Networks: an Empirical Study

Jaehoon Lee, Samuel S. Schoenholz, Jeffrey Pennington +4

We perform a careful, thorough, and large scale empirical study of the correspondence between wide neural networks and kernel methods. By doing so, we resolve a variety of open que…

stat.ML2020

Exact posterior distributions of wide Bayesian neural networks

Jiri Hron, Yasaman Bahri, Roman Novak +2

Recent work has shown that the prior over functions induced by a deep Bayesian neural network (BNN) behaves as a Gaussian process (GP) as the width of all layers becomes large. How…

cs.LG2024

Scaling Exponents Across Parameterizations and Optimizers

Katie Everett, Lechao Xiao, Mitchell Wortsman +8

Robust and effective scaling of models from small to large width typically requires the precise adjustment of many algorithmic and architectural details, such as parameterization a…

stat.ML2018

Deep Neural Networks as Gaussian Processes

Jaehoon Lee, Yasaman Bahri, Roman Novak +3

It has long been known that a single-layer fully-connected neural network with an i.i.d. prior over its parameters is equivalent to a Gaussian process (GP), in the limit of infinit…

stat.ML2018

Sensitivity and Generalization in Neural Networks: an Empirical Study

Roman Novak, Yasaman Bahri, Daniel A. Abolafia +2

In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classica…

cs.LG2022

Fast Neural Kernel Embeddings for General Activations

Insu Han, Amir Zandieh, Jaehoon Lee +3

Infinite width limit has shed light on generalization and optimization aspects of deep learning by establishing connections between neural networks and kernel methods. Despite thei…

stat.ML2020

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

Roman Novak, Lechao Xiao, Jaehoon Lee +6

There is a previously identified equivalence between wide fully connected neural networks (FCNs) and Gaussian processes (GPs). This equivalence enables, for instance, test set pred…

cs.LG2020

On the infinite width limit of neural networks with a standard parameterization

Jascha Sohl-Dickstein, Roman Novak, Samuel S. Schoenholz +1

There are currently two parameterizations used to derive fixed kernels corresponding to infinite width neural networks, the NTK (Neural Tangent Kernel) parameterization and the nai…

cs.CV2016

Exploring the Neural Algorithm of Artistic Style

Yaroslav Nikulin, Roman Novak

We explore the method of style transfer presented in the article "A Neural Algorithm of Artistic Style" by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge (arXiv:1508.06576).…

cs.CL2023

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…

stat.ML2020

Infinite attention: NNGP and NTK for deep attention networks

Jiri Hron, Yasaman Bahri, Jascha Sohl-Dickstein +1

There is a growing amount of literature on the relationship between wide neural networks (NNs) and Gaussian processes (GPs), identifying an equivalence between the two for a variet…

cs.LG2023

Small-scale proxies for large-scale Transformer training instabilities

Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13

Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…

stat.ML2019

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Jaehoon Lee, Lechao Xiao, Samuel S. Schoenholz +4

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have mad…

cs.LG2022

Fast Finite Width Neural Tangent Kernel

Roman Novak, Jascha Sohl-Dickstein, Samuel S. Schoenholz

The Neural Tangent Kernel (NTK), defined as where $\left[\…

cs.CL2018

Iterative Refinement for Machine Translation

Roman Novak, Michael Auli, David Grangier

Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be…

cs.CV2016

Improving the Neural Algorithm of Artistic Style

Roman Novak, Yaroslav Nikulin

In this work we investigate different avenues of improving the Neural Algorithm of Artistic Style (by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge, arXiv:1508.06576). Whil…

cs.LG2024

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Avi Singh, John D. Co-Reyes, Rishabh Agarwal +38

Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of hi…

stat.ML2022

Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling

Jiri Hron, Roman Novak, Jeffrey Pennington +1

We introduce repriorisation, a data-dependent reparameterisation which transforms a Bayesian neural network (BNN) posterior to a distribution whose KL divergence to the BNN prior v…

cs.CL2024

Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability

Jiri Hron, Laura Culp, Gamaleldin Elsayed +28

While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come i…

cs.CL2023

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

C. Daniel Freeman, Laura Culp, Aaron Parisi +27

We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic…

cs.LG2022

Dataset Distillation with Infinitely Wide Convolutional Networks

Timothy Nguyen, Roman Novak, Lechao Xiao +1

The effectiveness of machine learning algorithms arises from being able to extract useful features from large amounts of data. As model and dataset sizes increase, dataset distilla…

stat.ML2019

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Roman Novak, Lechao Xiao, Jiri Hron +4

Neural Tangents is a library designed to enable research into infinite-width neural networks. It provides a high-level API for specifying complex and hierarchical neural network ar…