ICML 2024 Selected poster Collection (1)

1.On Discrete Prompt Optimization for Diffusion Models

This paper introduces the first gradient-based framework for prompt optimization in text-to-image diffusion models. We formulate prompt engineering as a discrete optimization problem over the language space. Two major challenges arise in efficiently finding a solution to this problem: (1) Enormous Domain Space: Setting the domain to the entire language space poses significant difficulty to the optimization process. (2) Text Gradient: Efficiently computing the text gradient is challenging, as it requires backpropagating through the inference steps of the diffusion model and a non-differentiable embedding lookup table. Beyond the problem formulation, our main technical contributions lie in solving the above challenges. First, we design a family of dynamically generated compact subspaces comprised of only the most relevant words to user input, substantially restricting the domain space. Second, we introduce “Shortcut Text Gradient” — an effective replacement for the text gradient that can be obtained with constant memory and runtime. Empirical evaluation on prompts collected from diverse sources (DiffusionDB, ChatGPT, COCO) suggests that our method can discover prompts that substantially improve (prompt enhancement) or destroy (adversarial attack) the faithfulness of images generated by the text-to-image diffusion model.

2.Multi-View Clustering by Inter-cluster Connectivity Guided Reward

Multi-view clustering has been widely explored for its effectiveness in harmonizing heterogeneity along with consistency in different views of data. Despite the significant progress made by recent works, the performance of most existing methods is heavily reliant on strong priori information regarding the true cluster number , which is rarely feasible in real-world scenarios. In this paper, we propose a novel graph-based multi-view clustering algorithm to infer unknown  through a graph consistency reward mechanism. To be specific, we evaluate the cluster indicator matrix during each iteration with respect to diverse . We formulate the inference process of unknown  as a parsimonious reinforcement learning paradigm, where the reward is measured by inter-cluster connectivity. As a result, our approach is capable of independently producing the final clustering result, free from the input of a predefined cluster number. Experimental results on multiple benchmark datasets demonstrate the effectiveness of our proposed approach in comparison to existing state-of-the-art methods.

3.Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional agents. However, many of these techniques have been tested in limited settings, often on tasks from single simulation benchmarks and against well-known algorithms rather than a range of regularization approaches. This limits our understanding of the specific mechanisms driving RL improvements. To address this, we implemented over 60 different off-policy agents, each integrating established regularization techniques from recent state-of-the-art algorithms. We tested these agents across 14 diverse tasks from 2 simulation benchmarks, measuring training metrics related to overestimation, overfitting, and plasticity loss — issues that motivate the examined regularization techniques. Our findings reveal that while the effectiveness of a specific regularization setup varies with the task, certain combinations consistently demonstrate robust and superior performance. Notably, a simple Soft Actor-Critic agent, appropriately regularized, reliably finds a better-performing policy within the training regime, which previously was achieved mainly through model-based approaches.

4.Copyright Traps for Large Language Models 

Questions of fair use of copyright-protected content to train Large Language Models (LLMs) are being actively debated. Document-level inference has been proposed as a new task: inferring from black-box access to the trained model whether a piece of content has been seen during training. SOTA methods however rely on naturally occurring memorization of (part of) the content. While very effective against models that memorize significantly, we hypothesize – and later confirm – that they will not work against models that do not naturally memorize, e.g. medium-size 1B models. We here propose to use copyright traps, the inclusion of fictitious entries in original content, to detect the use of copyrighted materials in LLMs with a focus on models where memorization does not naturally occur. We carefully design a randomized controlled experimental setup, inserting traps into original content (books) and train a 1.3B LLM from scratch. We first validate that the use of content in our target model would be undetectable using existing methods. We then show, contrary to intuition, that even medium-length trap sentences repeated a significant number of times (100) are not detectable using existing methods. However, we show that longer sequences repeated a large number of times can be reliably detected (AUC=0.75) and used as copyright traps. Beyond copyright applications, our findings contribute to the study of LLM memorization: the randomized controlled setup enables us to draw causal relationships between memorization and certain sequence properties such as repetition in model training data and perplexity.

5.Implicit meta-learning may lead language models to trust more reliable sources 

We demonstrate that large language models (LLMs) may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings (“tags”) as indicators of usefulness in a synthetic fine-tuning dataset. Fine-tuning on this dataset leads to implicit meta-learning (IML): in further fine-tuning, the model updates to make more use of text that is tagged as useful. We perform a thorough empirical investigation of this phenomenon, finding (among other things) that (i) it occurs in both pretrained LLMs and those trained from scratch, as well as on a vision task, and (ii) larger models and smaller batch sizes tend to give more IML. We also use probing to examine how IML changes the way models store knowledge in their parameters. Finally, we reflect on what our results might imply about the capabilities, risks, and controllability of future AI systems.

6.Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming

Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strategy of dreaming itself. Therefore, it is a question whether and how an agent can “dream better’’ in a more structured and strategic way. In this paper, inspired by the observation from cognitive science suggesting that humans use a spatial divide-and-conquer strategy in planning, we propose a new MBRL agent, called Dr. Strategy, which is equipped with a novel Dreaming Strategy. The proposed agent realizes a version of divide-and-conquer-like strategy in dreaming. This is achieved by learning a set of latent landmarks and then utilizing these to learn a landmark-conditioned highway policy. With the highway policy, the agent can first learn in the dream to move to a landmark, and from there it tackles the exploration and achievement task in a more focused way. In experiments, we show that the proposed model outperforms prior pixel-based MBRL methods in various visually complex and partially observable navigation tasks.

7.When Will Gradient Regularization Be Harmful? 

Gradient regularization (GR), which aims to penalize the gradient norm atop the loss function, has shown promising results in training modern over-parameterized deep neural networks. However, can we trust this powerful technique? This paper reveals that GR can cause performance degeneration in adaptive optimization scenarios, particularly with learning rate warmup. Our empirical and theoretical analyses suggest this is due to GR inducing instability and divergence in gradient statistics of adaptive optimizers at the initial training stage. Inspired by the warmup heuristic, we propose three GR warmup strategies, each relaxing the regularization effect to a certain extent during the warmup course to ensure the accurate and stable accumulation of gradients. With experiments on Vision Transformer family, we confirm the three GR warmup strategies can effectively circumvent these issues, thereby largely improving the model performance. Meanwhile, we note that scalable models tend to rely more on the GR warmup, where the performance can be improved by up to 3% on Cifar10 compared to baseline GR.

PDF：https://openreview.net/pdf?id=60vC1FY0dZhttps://openreview.net/pdf?id=60vC1FY0dZ

Code is available at: https://github.com/zhaoyang-0204/gnp.

8.Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond

In this paper, we investigate the empirical counterpart of Group Distributionally Robust Optimization (GDRO), which aims to minimize the maximal empirical risk across  distinct groups. We formulate empirical GDRO as a two-level finite-sum convex-concave minimax optimization problem and develop an algorithm called ALEG to benefit from its special structure. ALEG is a double-looped stochastic primal-dual algorithm that incorporates variance reduction techniques into a modified mirror prox routine. To exploit the two-level finite-sum structure, we propose a simple group sampling strategy to construct the stochastic gradient with a smaller Lipschitz constant and then perform variance reduction for all groups. Theoretical analysis shows that ALEG achieves -accuracy within a computation complexity of , where is the average number of samples among  groups. Notably, our approach outperforms the state-of-the-art method by a factor of . Based on ALEG, we further develop a two-stage optimization algorithm called ALEM to deal with the empirical Minimax Excess Risk Optimization (MERO) problem. The computation complexity of ALEM nearly matches that of ALEG, surpassing the rates of existing methods.

PDF：https://openreview.net/pdf?id=pOJbk4Nzmi

9.Evaluation of Trajectory Distribution Predictions with Energy Score

Predicting the future trajectory of surrounding objects is inherently uncertain and vital in the safe and reliable planning of autonomous systems such as in self-driving cars. Although trajectory prediction models have become increasingly sophisticated in dealing with the complexities of spatiotemporal data, the evaluation methods used to assess these models have not kept pace. “Minimum of N” is a common family of metrics used to assess the rich outputs of such models. We critically examine the Minimum of N within the proper scoring rules framework to show that it is not strictly proper and demonstrate how that could lead to a misleading assessment of multimodal trajectory predictions. As an alternative, we propose using Energy Score-based evaluation measures, leveraging their proven propriety for a more reliable evaluation of trajectory distribution predictions.

PDF:https://openreview.net/pdf?id=FCmWhJQ14I

10.Causal Discovery with Fewer Conditional Independence Tests

Many questions in science center around the fundamental problem of understanding causal relationships. However, most constraint-based causal discovery algorithms, including the well-celebrated PC algorithm, often incur an exponential number of conditional independence (CI) tests, posing limitations in various applications. Addressing this, our work focuses on characterizing what can be learned about the underlying causal graph with a reduced number of CI tests. We show that it is possible to a learn a coarser representation of the hidden causal graph with a polynomial number of tests. This coarser representation, named Causal Consistent Partition Graph (CCPG), comprises of a partition of the vertices and a directed graph defined over its components. CCPG satisfies consistency of orientations and additional constraints which favor finer partitions. Furthermore, it reduces to the underlying causal graph when the causal graph is identifiable. As a consequence, our results offer the first efficient algorithm for recovering the true causal graph with a polynomial number of tests, in special cases where the causal graph is fully identifiable through observational data and potentially additional interventions.

PDF：https://openreview.net/pdf?id=HpT19AKddu