Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.32175

Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information

Xincheng Xu·Thilina Ranbaduge·Thierry Rakotoarivelo·David Smith
View original source ↗Read source document ↗Export metadata ↓

Abstract

Differentially Private Stochastic Gradient Descent (DPSGD) has become the de facto standard for training deep neural networks with rigorous privacy guarantees. However, the utility of DPSGD is constrained by gradient clipping bias and DP noise. While existing work has tried to address these issues, the geometric misalignment caused by clipping bias remains a critical challenge. To bridge this gap, we propose a novel framework, Curvature-Aware Differentially Private Stochastic Gradient Descent (CA-DPSGD), which leverages approximate second-order information to construct an optimal, curvature-aware clipping space. CA-DPSGD integrates a rectified estimator for the curvature matrix and is coupled with an anisotropic noise mechanism to ensure privacy guarantees. Extensive empirical experiments demonstrate that our approach outperforms state-of-the-art clipping methods.

Explore related subjects

cs.LGcs.CR

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xincheng Xu, Thilina Ranbaduge, Thierry Rakotoarivelo, David Smith. 2026-10-23. Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information. https://arxiv.org/abs/2610.32175

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

FlashNorm: Fast Normalization for Transformers

Normalization layers are ubiquitous in large language models (LLMs) yet represent a compute bottleneck: on hardware with distinct vector and matrix execution units, the RMS calculation blocks the subsequent matrix multiplication, preventing parallel execution. We present FlashNorm, an exact reformulation of RMSNorm followed by a linear layer that (i) eliminates the normalization weights by folding them into the subsequent linear layer, and (ii) defers the scalar RMS normalization to the output of the matrix multiplication, enabling the two operations to execute in parallel. Additionally, by the scale invariance of RMS, an RMSNorm followed by a linear layer followed by another RMSNorm allows the first RMSNorm to be eliminated entirely -- a mathematically identical simplification that removes the pre-attention RMSNorm in models using QKV-normalization (e.g., Gemma~4) and in MLA-models with latent normalization (e.g., DeepSeek-V2, Mistral Small 4, and OpenMythos). The same techniques extend to LayerNorm, Dynamic Tanh (DyT), feed-forward networks with GLU variants, and RoPE-based attention. On an NVIDIA T4 GPU, FlashNorm achieves 33 - 35% lower latency on the norm-then-project operation in the compute-bound (prefill) regime at SmolLM2-135M scale, and 12 - 14% at Llama-7B scale. We verify zero-loss weight folding on three models. Beyond inference speed, FlashNorm simplifies model implementations by reducing parameter tensor count. Watch our explainer video https://youtu.be/GEuJv34_XgU?si and see https://github.com/OpenMachine-ai/transformer-tricks for code.

cs.LG↗
arXiv2026

Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA

Slim attention shrinks the context memory size by 2x for transformer models with MHA (multi-head attention), which can speed up inference by up to 2x for large context windows. Slim attention is an exact, mathematically identical implementation of the standard attention mechanism and therefore doesn't compromise model accuracy. In other words, slim attention losslessly compresses the context memory by a factor of 2. For encoder-decoder transformers, the context memory size can be reduced even further: For the Whisper models for example, slim attention reduces the context memory by 8x, which can speed up token generation by 5x for batch size 64 for example. And for the T5-11B model for example, the memory can be reduced by 32x because its MHA projection dimension is larger than the embedding dimension. See https://github.com/OpenMachine-ai/transformer-tricks for code and more transformer tricks, and https://www.youtube.com/watch?v=uVtk3B6YO4Y for this paper's YouTube video.

cs.LG↗
arXiv2026

MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about memorized private data, outdated knowledge, and harmful content. Existing unlearning approaches for MLLMs typically adapt training-based strategies such as gradient ascent or preference optimization, but these methods are computationally expensive, irreversible, and often distort retained knowledge. In this work, we propose MLLMEraser, an input-aware, training-free framework for test-time unlearning. Our approach leverages activation steering to enable dynamic knowledge erasure without parameter updates. Specifically, we construct a multimodal erasure direction by contrasting adversarially perturbed, knowledge-recall image-text pairs with knowledge-erasure counterparts, capturing both textual and visual discrepancies. To prevent unnecessary interference, we further design an input-aware steering mechanism that adaptively determines when and how the erasure direction should be applied, preserving utility on retained knowledge while enforcing forgetting on designated content. Experiments on LLaVA-1.5 and Qwen-2.5-VL demonstrate that MLLMEraser consistently outperforms state-of-the-art MLLM unlearning baselines, achieving stronger forgetting performance with lower computational cost and minimal utility degradation.

cs.LG↗