Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for disagreement, like in the training of large language models. We formalise and analyse the problem of learning a reward model that can be specialised to a user. Using the principle of empirical risk minimisation, we derive a probably approximately correct (PAC) bound showing the dependency of the approximation error on the number of training examples, as usual, and also on the number of human raters who provided feedback on them. Based on our theoretical findings, we discuss how to best collect pairwise preference data and argue that adaptive reward models should be beneficial when there is considerable disagreement among users. We also propose a concrete architecture for an adaptive reward model. Our approach leverages the observation that individual preferences can be captured as a linear combination of a set of general reward features. We show how to learn such features and subsequently use them to quickly adapt the reward model to a specific individual, even if their preferences are not reflected in the training data. We present experiments with large language models illustrating our theoretical results and comparing the proposed architecture with a non-adaptive baseline. Consistent with our analysis, the benefits provided by our model increase with the number of raters and the heterogeneity of their preferences. We also show that our model compares favourably to adaptive counterparts, including those performing in-context personalisation.

Modeling attacks, in which an adversary uses machine learning techniques to model a hardware-based Physically Unclonable Function (PUF) pose a great threat to the viability of these hardware security primitives. In most modeling attacks, a random subset of challenge-response-pairs (CRPs) are used as the labeled data for the machine learning algorithm. Here, for the arbiter-PUF, a delay based PUF which may be viewed as a linear threshold function with random weights (due to manufacturing imperfections), we investigate the role of active learning in Support Vector Machine (SVM) learning. We focus on challenge selection to help SVM algorithm learn “fast” and learn “slow”. Our methods construct challenges rather than relying on a sample pool of challenges as in prior work. Using active learning to learn “fast” (less CRPs revealed, higher accuracies) may help manufacturers learn the manufactured PUFs more efficiently, or may form a more powerful attack when the attacker may query the PUF for CRPs at will. Using active learning to select challenges from which learning is “slow” (low accuracy despite a large number of revealed CRPs) may provide a basis for slowing down attackers who are limited to overhearing CRPs.

Source-free domain adaptation (SFDA) is compelling because it allows adapting an off-the-shelf model to a new domain using only unlabelled data. In this work, we apply existing SFDA techniques to a challenging set of naturally-occurring distribution shifts in bioacoustics, which are very different from the ones commonly studied in computer vision. We find existing methods perform differently relative to each other than observed in vision benchmarks, and sometimes perform worse than no adaptation at all. We propose a new simple method which outperforms the existing methods on our new shifts while exhibiting strong performance on a range of vision datasets. Our findings suggest that existing SFDA methods are not as generalizable as previously thought and that considering diverse modalities can be a useful avenue for designing more robust models.

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with ImageNet classifier weights and fine-tuned on the object detection task. Recent works show this is not strictly necessary under longer training regimes and provide recipes for training the backbone from scratch. We investigate the opposite direction of this end-to-end training trend: we show that an extreme form of knowledge preservation-freezing the classifier-initialized backbone— consistently improves many different detection models, and leads to considerable resource savings. We hypothesize and corroborate experimentally that the remaining detector components capacity and structure is a crucial factor in leveraging the frozen backbone. Immediate applications of our findings include performance improvements on hard cases like detection of long-tail object classes and computational and memory resource savings that contribute to making the field more accessible to researchers with access to fewer computational resources.

Arbiter Physically Unclonable Functions (APUFs) are hardware security primitives that exploit manufacturing random-ness to generate unique digital fingerprints for ICs. This paper theoretically and numerically examines the impact of faults native to APUFs - mask parameter faults from the design phase, or process variation (PV) during the manufacturing phase. We model them statistically, and explain quantitatively how these faults affect the resulting APUF bias and uniqueness. On a single APUF instance, these faults manifest as some outlier delta elements in magnitude, thus we focus on such abnormal delta elements when addressing APUF faults. To detect such bad APUF instances and diagnose the abnormal delta elements, we propose a testing methodology which partitions a random set of challenges so that a specific delta element can be targeted, forming a perceivable bias in the responses over these sets. This low-cost approach is highly effective in detecting and diagnosing bad APUFs with abnormal delta element(s).

Transfer-learning methods aim to improve performance in a data-scarce target domain using a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing, involves freezing the source model and training a new classification head for the target domain. This strategy is outperformed by a more costly but state-of-the-art method – fine-tuning all parameters of the source model to the target domain – possibly because fine-tuning allows the model to leverage useful information from intermediate layers which is otherwise discarded by the later previously trained layers. We explore the hypothesis that these intermediate layers might be directly exploited. We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain. In evaluations on the Visual Task Adaptation Benchmark-1k, Head2Toe matches performance obtained with fine-tuning on average while reducing training and storage cost hundred folds or more, but critically, for out-of-distribution transfer, Head2Toe outperforms fine-tuning. Code used in our experiments can be found in supplementary materials.

We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limitations in widely used architectures. Drawing insights from frequency analysis theory, we take a closer look at ResNet and EfficientNet architectures and review the trade-off between aliasing and information loss in each of their major components. We show how to mitigate aliasing by inserting non-trainable low-pass filters at key locations, particularly where networks lack the capacity to learn them. These simple architectural changes lead to substantial improvements in generalization on i.i.d. and even more on out-of-distribution conditions, such as image classification under natural corruptions on ImageNet-C [11] and few-shot learning on Meta-Dataset [26]. State-of-the art results are achieved on both datasets without introducing additional trainable parameters and using the default hyper-parameters of open source codebases.

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from \emph{new datasets} using only a few examples. To this end, we propose to utilize the diverse training set to construct a \emph{universal template}: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.

From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made dramatic advances with artificial agents reaching superhuman performance in challenge domains like Go, Atari, and some variants of poker. As with their predecessors of chess, checkers, and backgammon, these game domains have driven research by providing sophisticated yet well-defined challenges for artificial intelligence practitioners. We continue this tradition by proposing the game of Hanabi as a new challenge domain with novel problems that arise from its combination of purely cooperative gameplay with two to five players and imperfect information. In particular, we argue that Hanabi elevates reasoning about the beliefs and intentions of other agents to the foreground. We believe developing novel techniques for such theory of mind reasoning will not only be crucial for success in Hanabi, but also in broader collaborative efforts, especially those with human partners. To facilitate future research, we introduce the open-source Hanabi Learning Environment, propose an experimental framework for the research community to evaluate algorithmic advances, and assess the performance of current state-of-the-art techniques.

We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications, and 4) generalize well to challenging, new data from few examples or even zero-shot.

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only poor samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models with continuous generators. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.

Restricted Boltzmann machines (RBMs) are powerful machine learning models, but learning and some kinds of inference in the model require sampling-based approximations, which, in classical digital computers, are implemented using expensive MCMC. Physical computation offers the opportunity to reduce the costof sampling by building physical systems whose natural dynamics correspond to drawing samples from the desired RBM distribution. Such a system avoids the burn-in and mixing cost of a Markov chain. However, hardware implementations of this variety usually entail limitations such as low-precision and limited range of the parameters and restrictions on the size and topology of the RBM. We conduct software simulations to determine how harmful each of these restrictions is. Our simulations are based on the D-Wave Two computer, but the issues we investigate arise in most forms of physical computation.Our findings suggest that designers of new physical computing hardware and algorithms for physical computers should focus their efforts on overcoming the limitations imposed by the topology restrictions of currently existing physical computers.