RLRobert Lange

Robert Lange

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Robert Lange has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Competition and Attraction Improve Model Fusion

    by João Abrantes, Robert Lange, Yujin Tang


  • Open Access

    Evolution Transformer: In-Context Evolutionary Optimization

    by Robert Lange, Yingtao Tian, Yujin Tang

    Evolutionary optimization algorithms are often derived from loose biological analogies and struggle to leverage information obtained during the sequential course of optimization. An alternative promising approach is to leverage data and directly discover powerful optimization principles via meta-optimization. In this work, we follow such a paradigm and introduce Evolution Transformer, a causal Transformer architecture, which can flexibly characterize a family of Evolution Strategies. Given a trajectory of evaluations and search distribution statistics, Evolution Transformer outputs a performance-improving update to the search distribution. The architecture imposes a set of suitable inductive biases, i.e. the invariance of the distribution update to the order of population members within a generation and equivariance to the order of the search dimensions. We train the model weights using Evolutionary Algorithm Distillation, a technique for supervised optimization of sequence models using teacher algorithm trajectories. The resulting model exhibits strong in-context optimization performance and shows strong generalization capabilities to otherwise challenging neuroevolution tasks. We analyze the resulting properties of the Evolution Transformer and propose a technique to fully self-referentially train the Evolution Transformer, starting from a random initialization and bootstrapping its own learning progress. We provide an open source implementation under https://github.com/RobertTLange/evosax.


  • Open Access

    Large Language Models As Evolution Strategies

    by Robert Lange, Yingtao Tian, Yujin Tang

    Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms. These include gradient descent, classification, sequence completion, transformation, and improvement. In this work, we investigate whether large language models (LLMs), which never explicitly encountered the task of black-box optimization, are in principle capable of implementing evolutionary optimization algorithms. While previous works have solely focused on language-based task specification, we move forward and focus on the zero-shot application of LLMs to black-box optimization. We introduce a novel prompting strategy, consisting of least-to-most sorting of discretized population members and querying the LLM to propose an improvement to the mean statistic, i.e. perform a type of black-box recombination operation. Empirically, we find that our setup allows the user to obtain an LLM-based evolution strategy, which we call 'EvoLLM', that robustly outperforms baseline algorithms such as random search and Gaussian Hill Climbing on synthetic BBOB functions as well as small neuroevolution tasks. Hence, LLMs can act as 'plug-in' in-context recombination operators. We provide several comparative studies of the LLM's model size, prompt strategy, and context construction. Finally, we show that one can flexibly improve EvoLLM's performance by providing teacher algorithm information via instruction fine-tuning on previously collected teacher optimization trajectories.


  • Open Access

    Discovering Evolution Strategies via Meta-Black-Box Optimization

    by Robert Lange, Tom Schaul, Yutian Chen, Tom Zahavy, Valentin Dalibard, Chris Lu, Satinder Singh, Sebastian Flennerhag


  • Open Access

    evosax: JAX-Based Evolution Strategies

    by Robert Tjarko Lange

    The deep learning revolution has greatly been accelerated by the 'hardware lottery': Recent advances in modern hardware accelerators, compilers and the availability of open-source software paved the way for large-scale batch gradient optimization. Evolutionary optimization, on the other hand, has mainly relied on CPU-parallelism, e.g. using Dask scheduling and distributed multi-host infrastructure. Here we argue that also modern evolutionary computation can significantly benefit from the massive computational throughput provided by GPUs and TPUs. In order to better harness these resources and to enable the next generation of black-box optimization algorithms, we release evosax : A JAX-based library of evolution strategies which allows researchers to leverage powerful function transformations such as just-in-time compilation, automatic vectorization and hardware parallelization.1 evosax implements 30 evolutionary optimization algorithms including finite-difference-based, estimation-of-distribution evolution strategies and various genetic algorithms. Every single algorithm can directly be executed on hardware accelerators and automatically vectorized or parallelized across devices using a single line of code. It is designed in a modular fashion and allows for flexible usage via a simple ask-evaluate-tell API. We thereby hope to facilitate a new wave of scalable evolutionary optimization algorithms.


  • Open Access

    Lottery tickets in evolutionary optimization: On sparse backpropagation-free trainability

    by Robert Lange, Henning Sprekeler

    Lottery tickets in Deep Learning [2] refer to highly sparse neural network initializations, which train to the performance level of their dense counterparts The existence of such sparse trainable initializations has previously been documented for a variety of gradient-based training settings. But is the lottery ticket phenomenon an idiosyncrasy of stochastic gradient descent or does it generalize to evolutionary optimization? In this paper we establish the existence of highly sparse trainable initializations for evolution strategies (ES) and characterize qualitative differences compared to gradient descent (GD)-based sparse training. We introduce a novel signal-to-noise (SNR) iterative pruning procedure, which extracts evolvable sub-networks and incorporates loss curvature information into the network pruning step. We demonstrate the existence of highly sparse evolvable initializations for a wide range of network architectures, evolution strategies and task settings. Furthermore, we find that these initializations encode an inductive bias, which transfers across different evolution strategies, related tasks and even GD-based training. Finally, we compare the local optima resulting from the different optimization paradigms and sparsity levels. In contrast to GD, ES explore diverse and flat local optima and do not preserve linear mode connectivity across sparsity levels and independent runs. The full paper was accepted at the ICML conference [4].


  • Open Access

    Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization

    by Robert Lange, Tom Schaul, Yutian Chen, Chris Lu, Tom Zahavy, Valentin Dalibard, Sebastian Flennerhag

    Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution. While they provide a general-purpose tool for optimization, their particular instantiations can be heuristic and motivated by loose biological intuition. In this work we explore a fundamentally different approach: Given a sufficiently flexible parametrization of the genetic operators, we discover entirely new genetic algorithms in a data-driven fashion. More specifically, we parametrize selection and mutation rate adaptation as cross- and self-attention modules and use Meta-Black-Box-Optimization to evolve their parameters on a set of diverse optimization tasks. The resulting Learned Genetic Algorithm outperforms state-of-the-art adaptive baseline genetic algorithms and generalizes far beyond its meta-training settings. The learned algorithm can be applied to previously unseen optimization problems, search dimensions & evaluation budgets. We conduct extensive analysis of the discovered operators and provide ablation experiments, which highlight the benefits of flexible module parametrization and the ability to transfer ('plug-in') the learned operators to conventional genetic algorithms.


  • Enhancing agency in career development via cognitive information processing theory

    by Seth C. W. Hayden, Debra S. Osborn, Carley Peace, Robert Lange

    The interconnected aspects of career and mental health posit career as a central feature of human functioning. A perceived lack of control within career and work exacerbates existing challenges associated with COVID-19. Focusing on enhancing agency within the realm of career and work is imperative within counselling. Cognitive Information Processing (CIP) accounts for the complexity of career concerns by enhancing agency in career decision making, with problem solving serving as a conduit between uncertainty and empowerment. The current state of employment, threats to agency within career development, and specific CIP-based interventions to enhance agency are discussed.