{"work":{"id":"ab8da7fe-9ff3-44e6-9132-11d17ceef8c2","openalex_id":null,"doi":null,"arxiv_id":"1805.06085","raw_key":null,"title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","authors":null,"authors_text":"Choi, J","year":2018,"venue":"cs.CV","abstract":"Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. To address this cost, a number of quantization schemes have been proposed - but most of these techniques focused on quantizing weights, which are relatively smaller in size compared to activations. This paper proposes a novel quantization scheme for activations during training - that enables neural networks to work well with ultra low precision weights and activations without any significant accuracy degradation. This technique, PArameterized Clipping acTivation (PACT), uses an activation clipping parameter $\\alpha$ that is optimized during training to find the right quantization scale. PACT allows quantizing activations to arbitrary bit precisions, while achieving much better accuracy relative to published state-of-the-art quantization schemes. We show, for the first time, that both weights and activations can be quantized to 4-bits of precision while still achieving accuracy comparable to full precision networks across a range of popular models and datasets. We also show that exploiting these reduced-precision computational units in hardware can enable a super-linear improvement in inferencing performance due to a significant reduction in the area of accelerator compute engines coupled with the ability to retain the quantized model and activation data in on-chip memories.","external_url":"https://arxiv.org/abs/1805.06085","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-24T08:29:11.233090+00:00","pith_arxiv_id":"1805.06085","created_at":"2026-05-09T06:30:44.119027+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","render_title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks"},"hub":{"state":{"work_id":"ab8da7fe-9ff3-44e6-9132-11d17ceef8c2","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2023-06-01T17:59:10+00:00","last_pith_cited_at":"2026-05-21T11:38:52+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-08T18:24:07.437800+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}