ICLR 2024 Papers

Expert-level prompts, carefully engineered by human experts who have a deep understanding of both large language models (LLMs) and domain knowledge, are the future of prompting and pivotal to harnessing the full power of advanced LLMs. Discovering such prompts with an automated process remains a sought-after and unresolved challenge. Existing prompt optimization techniques, though automated through iterative sampling, often fall short in injecting domain knowledge and exploring the vast prompt space for complex expert-level prompts efficiently. To address this pressing need and achieve expert-level prompting, we introduce PromptAgent, which autonomously discovers prompts equivalent in quality to those handcrafted by experts. At its core, PromptAgent views prompt optimization as a strategic planning problem and employs a principled planning algorithm (rooted in Monte Carlo Tree Search) to strategically explore the vast expert-level prompt space. PromptAgent interacts with the LLM in a human-like trial-and-error manner during the planning, and injects expert-level knowledge by reflecting on model errors and generating insightful error feedback. This novel formulation allows it to iteratively evaluate intermediate prompts, refine them based on errors, simulate future rewards, and search for high-reward paths leading to expert-level prompts. We apply PromptAgent to 12 tasks spanning three practical domains: BIG-Bench Hard (BBH), domain-expert, and general NLU tasks, showing PromptAgent consistently outperforms strong prompting and prompt optimization baselines by great margins. Our qualitative analysis further emphasizes PromptAgent's capability to distill insightful errors into expert-level prompts.

In this study, we consider nonconvex federated learning problems with the existence of Byzantine workers. We propose a new simple Byzantine robust algorithm called Momentum Screening. The algorithm is adaptive to the Byzantine fraction, i.e., all its hyperparameters do not depend on the number of Byzantine workers. We show that our method achieves the best optimization error of $O(\delta^2\zeta_\mathrm{max}^2)$ for nonconvex smooth local objectives satisfying $\zeta_\mathrm{max}$-uniform gradient heterogeneity condition under $\delta$-Byzantine fraction, which can be better than the best known error rate of $O(\delta\zeta_\mathrm{mean}^2)$ for local objectives satisfying $\zeta_\mathrm{mean}$-mean heterogeneity condition when $\delta \leq (\zeta_\mathrm{max}/\zeta_\mathrm{mean})^2$. Furthermore, we derive an algorithm independent lower bound for local objectives satisfying $\zeta_\mathrm{max}$-uniform gradient heterogeneity condition and show the minimax optimality of our proposed method on this class. In numerical experiments, we validate the superiority of our method over the existing robust aggregation algorithms and verify our theoretical results.

Empirical studies have consistently demonstrated that increasing the size of neural networks often yields superior performance in practical applications. However, there is a lack of consensus regarding the appropriate scaling strategy, particularly when it comes to increasing the depth of neural networks. In practice, excessively large depths can lead to model performance degradation. In this paper, we introduce Depth-$\mu$P, a principled approach for depth scaling, allowing for the training of arbitrarily deep architectures while maximizing feature learning and diversity among nearby layers. Our method involves dividing the contribution of each residual block and the parameter update by the square root of the depth. Through the use of Tensor Programs, we rigorously establish the existence of a limit for infinitely deep neural networks under the proposed scaling scheme. This scaling strategy ensures more stable training for deep neural networks and guarantees the transferability of hyperparameters from shallow to deep models. To substantiate the efficacy of our scaling method, we conduct empirical validation on neural networks with depths up to $2^{10}$.

Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics. We make progress towards understanding the subtleties of training Transformers by carefully studying a simple yet canonical linearized *shallow* Transformer model. Specifically, we train linear Transformers to solve regression tasks, inspired by J. von Oswald et al. (ICML 2023), and K. Ahn et al. (NeurIPS 2023). Most importantly, we observe that our proposed linearized models can reproduce several prominent aspects of Transformer training dynamics. Consequently, the results obtained in this paper suggest that a simple linearized Transformer model could actually be a valuable, realistic abstraction for understanding Transformer optimization.

Machine learning approaches relying on such criteria as adversarial robustness or multi-agent settings have raised the need for solving game-theoretic equilibrium problems. Of particular relevance to these applications are methods targeting finite-sum structure, which generically arises in empirical variants of learning problems in these contexts. Further, methods with computable approximation errors are highly desirable, as they provide verifiable exit criteria. Motivated by these applications, we study finite-sum monotone inclusion problems, which model broad classes of equilibrium problems. Our main contributions are variants of the classical Halpern iteration that employ variance reduction to obtain improved complexity guarantees in which $n$ component operators in the finite sum are ``on average'' either cocoercive or Lipschitz continuous and monotone, with parameter $L$. The resulting oracle complexity of our methods, which provide guarantees for the last iterate and for a (computable) operator norm residual, is $\widetilde{\mathcal{O}}( n + \sqrt{n}L\varepsilon^{-1})$, which improves upon existing methods by a factor up to $\sqrt{n}$. This constitutes the first variance reduction-type result for general finite-sum monotone inclusions and for more specific problems such as convex-concave optimization when operator norm residual is the optimality measure. We further argue that, up to poly-logarithmic factors, this complexity is unimprovable in the monotone Lipschitz setting; i.e., the provided result is near-optimal.

Bilevel optimization problems appear in many widely used machine learning tasks. Bilevel optimization models are sensitive to small changes, and bilevel training tasks typically involve limited datasets. Therefore, overfitting is a common challenge in bilevel training tasks. This paper considers the use of dropout to address this problem. We propose a bilevel optimization model that depends on the distribution of dropout masks. We investigate how the dropout rate affects the hypergradient of this model. We propose a dropout bilevel method to solve the dropout bilevel optimization model. Subsequently, we analyze the resulting dropout bilevel method from an optimization perspective. Analyzing the optimization properties of methods with dropout is essential because it provides convergence guarantees for methods using dropout. However, there has been limited investigation in this research direction. We provide the complexity of the resulting dropout bilevel method in terms of reaching an $\epsilon$ stationary point of the proposed stochastic bilevel model. Empirically, we demonstrate that overfitting occurs in data cleaning problems, and the method proposed in this work mitigates this issue.