ICLR 2023 Papers

Humans have been shown to use a ''straightened'' encoding to represent the natural visual world as it evolves in time (Henaff et al. 2019). In the context of discrete video sequences, ''straightened'' means that changes between frames follow a more linear path in representation space at progressively deeper levels of processing. While deep convolutional networks are often proposed as models of human visual processing, many do not straighten natural videos. In this paper, we explore the relationship between network architecture, differing types of robustness, biologically-inspired filtering mechanisms, and representational straightness in response to time-varying input; we identify strengths and limitations of straightness as a useful way of evaluating neural network representations. We find that (1) adversarial training leads to straighter representations in both CNN and transformer-based architectures but (2) this effect is task-dependent, not generalizing to tasks such as segmentation and frame-prediction, where straight representations are not favorable for predictions; and nor to other types of robustness. In addition, (3) straighter representations impart temporal stability to class predictions, even for out-of-distribution data. Finally, (4) biologically-inspired elements increase straightness in the early stages of a network, but do not guarantee increased straightness in downstream layers of CNNs. We show that straightness is an easily computed measure of representational robustness and stability, as well as a hallmark of human representations with benefits for computer vision models.

Today, ground-truth generation uses data sets annotated by cloud-based annotation services. These services rely on human annotation, which can be prohibitively expensive. In this paper, we consider the problem of hybrid human-machine labeling, which trains a classifier to accurately auto-label part of the data set. However, training the classifier can be expensive too. We propose an iterative approach that minimizes total overall cost by, at each step, jointly determining which samples to label using humans and which to label using the trained classifier. We validate our approach on well known public data sets such as Fashion-MNIST, CIFAR-10, CIFAR-100, and ImageNet. In some cases, our approach has 6× lower overall cost relative to human labeling the entire data set, and is always cheaper than the cheapest competing strategy.

Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require many expert demonstrations. Can we instead cheaply design rewards using a natural language interface? This paper explores how to simplify reward design by using a large language model (LLM) such as GPT-3 as a proxy reward function, where the user provides a textual prompt containing a few examples (few-shot) or a description (zero-shot) of desired behavior. Our approach leverages this proxy reward function in an RL framework. Specifically, users specify a prompt once at the beginning of training. During training, the LLM evaluates an RL agent's behavior against the desired behavior described by the prompt and outputs a corresponding reward signal. The RL agent then uses this reward to update its behavior. We evaluate whether our approach can train agents aligned with user objectives in the Ultimatum Game, matrix games, and the DealOrNoDeal negotiation task. In all three tasks, we show that RL agents trained with our framework are well-aligned with the user's objectives and outperforms RL agents trained with reward functions learned via supervised learning.