Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task.

While current works account for the importance ofdepth for the expressivepower ofneural-networks, itremains an open question whether these benefits are exploited during a gradient-based optimization process.

Neural Information Processing Systems http://nips.cc/

Artificial intelligence has advanced rapidly through large neural networks trained on massive datasets using thousands of GPUs or TPUs. Such training can occupy entire data centers for weeks and requires enormous computational and energy resources. Yet the optimization algorithms behind these runs have not kept pace. Most large scale training still relies on synchronous methods, where workers must wait for the slowest device, wasting compute and amplifying the effects of hardware and network variability. Removing synchronization seems like a simple fix, but asynchrony introduces staleness, meaning updates computed on outdated models. This makes analysis difficult, especially when delays arise from system level randomness rather than algorithmic choices. As a result, the time complexity of asynchronous methods remains poorly understood. This dissertation develops a rigorous framework for asynchronous first order stochastic optimization, focusing on the core challenge of heterogeneous worker speeds. Within this framework, we show that with proper design, asynchronous SGD can achieve optimal time complexity, matching guarantees previously known only for synchronous methods. Our first contribution, Ringmaster ASGD, attains optimal time complexity in the homogeneous data setting by selectively discarding stale updates. The second, Ringleader ASGD, extends optimality to heterogeneous data, common in federated learning, using a structured gradient table mechanism. Finally, ATA improves resource efficiency by learning worker compute time distributions and allocating tasks adaptively, achieving near optimal wall clock time with less computation. Together, these results establish asynchronous optimization as a theoretically sound and practically efficient foundation for distributed learning, showing that coordination without synchronization can be both feasible and optimal.

Bayesian optimization (BO) is an attractive machine learning framework for performing sample-efficient global optimization of black-box functions. The optimization process is guided by an acquisition function that selects points to acquire in each round of BO. In batched BO, when multiple points are acquired in parallel, commonly used acquisition functions are often high-dimensional and intractable, leading to the use of sampling-based alternatives. We propose a statistical physics inspired acquisition function that can natively handle batches. Batched Energy-Entropy acquisition for BO (BEEBO) enables tight control of the explore-exploit trade-off of the optimization process and generalizes to heteroskedastic black-box problems. We demonstrate the applicability of BEEBO on a range of problems, showing competitive performance to existing acquisition functions.

Bayesian optimization (BO) is a popular method for computationally expensive black-box optimization. However, traditional BO methods need to solve new problems from scratch, leading to slow convergence. Recent studies try to extend BO to a transfer learning setup to speed up the optimization, where search space transfer is one of the most promising approaches and has shown impressive performance on many tasks. However, existing search space transfer methods either lack an adaptive mechanism or are not flexible enough, making it difficult to efficiently identify promising search space during the optimization process. In this paper, we propose a search space transfer learning method based on Monte Carlo tree search (MCTS), called MCTS-transfer, to iteratively divide, select, and optimize in a learned subspace. MCTS-transfer can not only provide a well-performing search space for warm-start but also adaptively identify and leverage the information of similar source tasks to reconstruct the search space during the optimization process. Experiments on synthetic functions, real-world problems, Design-Bench and hyper-parameter optimization show that MCTS-transfer can demonstrate superior performance compared to other search space transfer methods under different settings.

Understanding the power of depth in feed-forward neural networks is an ongoing challenge in the field of deep learning theory. While current works account for the importance of depth for the expressive power of neural-networks, it remains an open question whether these benefits are exploited during a gradient-based optimization process. In this work we explore the relation between expressivity properties of deep networks and the ability to train them efficiently using gradient-based algorithms. We give a depth separation argument for distributions with fractal structure, showing that they can be expressed efficiently by deep networks, but not with shallow ones. These distributions have a natural coarse-to-fine structure, and we show that the balance between the coarse and fine details has a crucial effect on whether the optimization process is likely to succeed. We prove that when the distribution is concentrated on the fine details, gradient-based algorithms are likely to fail. Using this result we prove that, at least in some distributions, the success of learning deep networks depends on whether the distribution can be approximated by shallower networks, and we conjecture that this property holds in general.

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every naturally occurring model of the world of which we are aware---e.g., a brain---arose as the byproduct of competing evolutionary pressures for survival, not minimization of a supervised forward-predictive loss via gradient descent. That useful models can arise out of the messy and slow optimization process of evolution suggests that forward-predictive modeling can arise as a side-effect of optimization under the right circumstances. Crucially, this optimization process need not explicitly be a forward-predictive loss. In this work, we introduce a modification to traditional reinforcement learning which we call observational dropout, whereby we limit the agents ability to observe the real environment at each timestep. In doing so, we can coerce an agent into learning a world model to fill in the observation gaps during reinforcement learning. We show that the emerged world model, while not explicitly trained to predict the future, can help the agent learn key skills required to perform well in its environment.

Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which enables thorough exploration and deliberation. Despite these advances, long-CoT LLMs often exhibit suboptimal reasoning behaviors, such as overthinking and excessively protracted reasoning chains, which can impair performance. In this paper, we analyze reasoning processes through an optimization lens, framing CoT as a gradient descent procedure where each reasoning step constitutes an update toward problem resolution. Building on this perspective, we introduce RePro (Rectifying Process-level Reward), a novel approach to refine LLM reasoning during post-training. RePro defines a surrogate objective function to assess the optimization process underlying CoT, utilizing a dual scoring mechanism to quantify its intensity and stability. These scores are aggregated into a composite process-level reward, seamlessly integrated into reinforcement learning with verifiable rewards (RLVR) pipelines to optimize LLMs. Extensive experiments across multiple reinforcement learning algorithms and diverse LLMs, evaluated on benchmarks spanning mathematics, science, and coding, demonstrate that RePro consistently enhances reasoning performance and mitigates suboptimal reasoning behaviors.