Goto

Collaborating Authors

 taxnodes:Technology: Instructional Materials


A Broader Impact & Ethics Statement

Neural Information Processing Systems

Note: Additional visualizations of our experiments can be found here: https://sites.google. AI-assisted teaching of motor control tasks can provide significant benefits such as more reliable teaching to individual students with different abilities (e.g. by leveraging more granular information about student actions), adaptability to any type of motor task or expert agent, and improved safety by reducing burden on human teachers for safety-critical tasks. However, we emphasize that our approach is solely meant to assist human teaching, as there exist many important aspects of human instruction that would be challenging to replace, including providing inspiration and motivation, in depth knowledge of human physical limitations, and an awareness of the broader context of a specific motor control task. Further risks of our approach, and avenues to address them, include: Bias of the expert agent. The suitability of the skills we use for teaching relies on how diverse the set of demonstrations from an expert is.



Online Adaptation of Language Models with a Memory of Amortized Contexts Jihoon Tack, Eric Mitchell

Neural Information Processing Systems

Due to the rapid generation and dissemination of information, large language models (LLMs) quickly run out of date despite enormous development costs. To address the crucial need to keep models updated, online learning has emerged as a critical tool when utilizing LLMs for real-world applications. However, given the ever-expanding corpus of unseen documents and the large parameter space of modern LLMs, efficient adaptation is essential. To address these challenges, we propose Memory of Amortized Contexts (MAC), an efficient and effective online adaptation framework for LLMs with strong knowledge retention. We propose a feature extraction and memory-augmentation approach to compress and extract information from new documents into compact modulations stored in a memory bank.



Towards Multi-dimensional Explanation Alignment for Medical Classification

Neural Information Processing Systems

The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understanding and visualization, as well as issues related to efficiency. To address these limitations, we propose a novel framework called Med-MICN (Medical Multidimensional Interpretable Concept Network). Med-MICN provides interpretability alignment for various angles, including neural symbolic reasoning, concept semantics, and saliency maps, which are superior to current interpretable methods. Its advantages include high prediction accuracy, interpretability across multiple dimensions, and automation through an end-to-end concept labeling process that reduces the need for extensive human training effort when working with new datasets. To demonstrate the effectiveness and interpretability of Med-MICN, we apply it to four benchmark datasets and compare it with baselines. The results clearly demonstrate the superior performance and interpretability of our Med-MICN.


Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation Chang Liu

Neural Information Processing Systems

Program verification is vital for ensuring software reliability, especially in the context of increasingly complex systems. Loop invariants, remaining true before and after each iteration of loops, are crucial for this verification process. Traditional provers and machine learning based methods for generating loop invariants often require expert intervention or extensive labeled data, and typically only handle numerical property verification.


Identifying Latent State-Transition Processes for Individualized Reinforcement Learning

Neural Information Processing Systems

The application of reinforcement learning (RL) involving interactions with individuals has grown significantly in recent years. These interactions, influenced by factors such as personal preferences and physiological differences, causally influence state transitions, ranging from health conditions in healthcare to learning progress in education. As a result, different individuals may exhibit different state-transition processes. Understanding individualized state-transition processes is essential for optimizing individualized policies. In practice, however, identifying these state-transition processes is challenging, as individual-specific factors often remain latent. In this paper, we establish the identifiability of these latent factors and introduce a practical method that effectively learns these processes from observed state-action trajectories. Experiments on various datasets show that the proposed method can effectively identify latent state-transition processes and facilitate the learning of individualized RL policies.


Prospective Learning: Learning for a Dynamic Future Ashwin De Silva,1 Rubing Yang,2

Neural Information Processing Systems

In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably approximately correct (PAC) learning, largely ignores time. As a consequence, existing strategies to address the dynamic nature of data and goals exhibit poor real-world performance. This paper develops a theoretical framework called "Prospective Learning" that is tailored for situations when the optimal hypothesis changes over time. In PAC learning, empirical risk minimization (ERM) is known to be consistent.


Label Delay in Online Continual Learning

Neural Information Processing Systems

A critical yet often overlooked aspect in online continual learning is the label delay, where new data may not be labeled due to slow and costly annotation processes. We introduce a new continual learning framework with explicit modeling of the label delay between data and label streams over time steps. In each step, the framework reveals both unlabeled data from the current time step t and labels delayed with d steps, from the time step t d. In our extensive experiments amounting to 25000 GPU hours, we show that merely increasing the computational resources is insufficient to tackle this challenge. Our findings highlight significant performance declines when solely relying on labeled data when the label delay becomes significant. More surprisingly, state-of-the-art Self-Supervised Learning and Test-Time Adaptation techniques that utilize the newer, unlabeled data, fail to surpass the performance of a naïve method that simply trains on the delayed supervised stream. To this end, we propose a simple, robust method, called Importance Weighted Memory Sampling that can effectively bridge the accuracy gap caused by label delay by prioritising memory samples that resemble the most to the newest unlabeled samples. We show experimentally that our method is the least affected by the label delay factor, and successfully recovers the accuracy of the non-delayed counterpart.


Appendix to: Predictive Querying for Autoregressive Neural Sequence Models 2

Neural Information Processing Systems

It is helpful to show both the exact summation form as well as the expected value representation as both will be useful in Section 4. Q3 The "hitting time" or the next occurrence of a specific event type a V is defined as τ(a). The value a V can be easily replaced with a set of values A V in these representations. Interestingly, we can see that Q3 is a generalization of Q2 by noting that they are identical when A = {}. In practice, computing this exactly is intractable due to it being an infinite sum. There are two potential approaches one could take to subvert this. The other option is to produce a lower bound on this expression by evaluating the sum in Eq. (11) for the first K terms. As such, if we evaluate Eq. (11) up to K terms for both p Similar to Q3, we can also ask this query with sets A B V instead of values a, b.